> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.vapi.ai/llms.txt. > For full documentation content, see https://docs.vapi.ai/llms-full.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vapi.ai/_mcp/server. # Delete Call DELETE https://api.vapi.ai/call/{id} Content-Type: application/json Reference: https://docs.vapi.ai/api-reference/calls/delete ## OpenAPI Specification ```yaml openapi: 3.1.0 info: title: api version: 1.0.0 paths: /call/{id}: delete: operationId: delete summary: Delete Call tags: - subpackage_calls parameters: - name: id in: path required: true schema: type: string - name: Authorization in: header description: Retrieve your API Key from [Dashboard](dashboard.vapi.ai). required: true schema: type: string responses: '200': description: '' content: application/json: schema: $ref: '#/components/schemas/Call' requestBody: content: application/json: schema: $ref: '#/components/schemas/DeleteCallDTO' servers: - url: https://api.vapi.ai components: schemas: DeleteCallDTO: type: object properties: ids: type: array items: type: string description: >- These are the Call IDs to be bulk deleted. If provided, the call ID if any in the request query will be ignored When requesting a bulk delete, updates when a call is deleted will be sent as a webhook to the server URL configured in the Org settings. It may take up to a few hours to complete the bulk delete, and will be asynchronous. title: DeleteCallDTO CallType: type: string enum: - inboundPhoneCall - outboundPhoneCall - webCall - vapi.websocketCall description: This is the type of call. title: CallType TransportCostType: type: string enum: - transport description: This is the type of cost, always 'transport' for this class. title: TransportCostType TransportCostProvider: type: string enum: - daily - vapi.websocket - twilio - vonage - telnyx - vapi.sip title: TransportCostProvider TransportCost: type: object properties: type: $ref: '#/components/schemas/TransportCostType' description: This is the type of cost, always 'transport' for this class. provider: $ref: '#/components/schemas/TransportCostProvider' minutes: type: number format: double description: >- This is the minutes of `transport` usage. This should match `call.endedAt` - `call.startedAt`. cost: type: number format: double description: This is the cost of the component in USD. required: - type - minutes - cost title: TransportCost TranscriberCostType: type: string enum: - transcriber description: This is the type of cost, always 'transcriber' for this class. title: TranscriberCostType TranscriberCostTranscriber: type: object properties: {} description: |- This is the transcriber that was used during the call. This matches one of the below: - `call.assistant.transcriber`, - `call.assistantId->transcriber`, - `call.squad[n].assistant.transcriber`, - `call.squad[n].assistantId->transcriber`, - `call.squadId->[n].assistant.transcriber`, - `call.squadId->[n].assistantId->transcriber`. title: TranscriberCostTranscriber TranscriberCost: type: object properties: type: $ref: '#/components/schemas/TranscriberCostType' description: This is the type of cost, always 'transcriber' for this class. transcriber: $ref: '#/components/schemas/TranscriberCostTranscriber' description: |- This is the transcriber that was used during the call. This matches one of the below: - `call.assistant.transcriber`, - `call.assistantId->transcriber`, - `call.squad[n].assistant.transcriber`, - `call.squad[n].assistantId->transcriber`, - `call.squadId->[n].assistant.transcriber`, - `call.squadId->[n].assistantId->transcriber`. minutes: type: number format: double description: >- This is the minutes of `transcriber` usage. This should match `call.endedAt` - `call.startedAt` for single assistant calls, while squad calls will have multiple transcriber costs one for each assistant that was used. cost: type: number format: double description: This is the cost of the component in USD. required: - type - transcriber - minutes - cost title: TranscriberCost ModelCostType: type: string enum: - model description: This is the type of cost, always 'model' for this class. title: ModelCostType ModelCostModel: type: object properties: {} description: |- This is the model that was used during the call. This matches one of the following: - `call.assistant.model`, - `call.assistantId->model`, - `call.squad[n].assistant.model`, - `call.squad[n].assistantId->model`, - `call.squadId->[n].assistant.model`, - `call.squadId->[n].assistantId->model`. title: ModelCostModel ModelCost: type: object properties: type: $ref: '#/components/schemas/ModelCostType' description: This is the type of cost, always 'model' for this class. model: $ref: '#/components/schemas/ModelCostModel' description: |- This is the model that was used during the call. This matches one of the following: - `call.assistant.model`, - `call.assistantId->model`, - `call.squad[n].assistant.model`, - `call.squad[n].assistantId->model`, - `call.squadId->[n].assistant.model`, - `call.squadId->[n].assistantId->model`. promptTokens: type: number format: double description: >- This is the number of prompt tokens used in the call. These should be total prompt tokens used in the call for single assistant calls, while squad calls will have multiple model costs one for each assistant that was used. completionTokens: type: number format: double description: >- This is the number of completion tokens generated in the call. These should be total completion tokens used in the call for single assistant calls, while squad calls will have multiple model costs one for each assistant that was used. cachedPromptTokens: type: number format: double description: >- This is the number of cached prompt tokens used in the call. This is only applicable to certain providers (e.g., OpenAI, Azure OpenAI) that support prompt caching. Cached tokens are billed at a discounted rate. cost: type: number format: double description: This is the cost of the component in USD. required: - type - model - promptTokens - completionTokens - cost title: ModelCost VoiceCostType: type: string enum: - voice description: This is the type of cost, always 'voice' for this class. title: VoiceCostType VoiceCostVoice: type: object properties: {} description: |- This is the voice that was used during the call. This matches one of the following: - `call.assistant.voice`, - `call.assistantId->voice`, - `call.squad[n].assistant.voice`, - `call.squad[n].assistantId->voice`, - `call.squadId->[n].assistant.voice`, - `call.squadId->[n].assistantId->voice`. title: VoiceCostVoice VoiceCost: type: object properties: type: $ref: '#/components/schemas/VoiceCostType' description: This is the type of cost, always 'voice' for this class. voice: $ref: '#/components/schemas/VoiceCostVoice' description: |- This is the voice that was used during the call. This matches one of the following: - `call.assistant.voice`, - `call.assistantId->voice`, - `call.squad[n].assistant.voice`, - `call.squad[n].assistantId->voice`, - `call.squadId->[n].assistant.voice`, - `call.squadId->[n].assistantId->voice`. characters: type: number format: double description: >- This is the number of characters that were generated during the call. These should be total characters used in the call for single assistant calls, while squad calls will have multiple voice costs one for each assistant that was used. cost: type: number format: double description: This is the cost of the component in USD. required: - type - voice - characters - cost title: VoiceCost VapiCostType: type: string enum: - vapi description: This is the type of cost, always 'vapi' for this class. title: VapiCostType VapiCostSubType: type: string enum: - normal - overage description: This is the sub type of the cost. title: VapiCostSubType VapiCost: type: object properties: type: $ref: '#/components/schemas/VapiCostType' description: This is the type of cost, always 'vapi' for this class. subType: $ref: '#/components/schemas/VapiCostSubType' description: This is the sub type of the cost. minutes: type: number format: double description: >- This is the minutes of Vapi usage. This should match `call.endedAt` - `call.startedAt`. cost: type: number format: double description: This is the cost of the component in USD. required: - type - subType - minutes - cost title: VapiCost VoicemailDetectionCostType: type: string enum: - voicemail-detection description: This is the type of cost, always 'voicemail-detection' for this class. title: VoicemailDetectionCostType VoicemailDetectionCostModel: type: object properties: {} description: This is the model that was used to perform the analysis. title: VoicemailDetectionCostModel VoicemailDetectionCostProvider: type: string enum: - twilio - google - openai - vapi description: This is the provider that was used to detect the voicemail. title: VoicemailDetectionCostProvider VoicemailDetectionCost: type: object properties: type: $ref: '#/components/schemas/VoicemailDetectionCostType' description: >- This is the type of cost, always 'voicemail-detection' for this class. model: $ref: '#/components/schemas/VoicemailDetectionCostModel' description: This is the model that was used to perform the analysis. provider: $ref: '#/components/schemas/VoicemailDetectionCostProvider' description: This is the provider that was used to detect the voicemail. promptTextTokens: type: number format: double description: >- This is the number of prompt text tokens used in the voicemail detection. promptAudioTokens: type: number format: double description: >- This is the number of prompt audio tokens used in the voicemail detection. completionTextTokens: type: number format: double description: >- This is the number of completion text tokens used in the voicemail detection. completionAudioTokens: type: number format: double description: >- This is the number of completion audio tokens used in the voicemail detection. cost: type: number format: double description: This is the cost of the component in USD. required: - type - model - provider - promptTextTokens - promptAudioTokens - completionTextTokens - completionAudioTokens - cost title: VoicemailDetectionCost AnalysisCostType: type: string enum: - analysis description: This is the type of cost, always 'analysis' for this class. title: AnalysisCostType AnalysisCostAnalysisType: type: string enum: - summary - structuredData - successEvaluation - structuredOutput description: This is the type of analysis performed. title: AnalysisCostAnalysisType AnalysisCostModel: type: object properties: {} description: This is the model that was used to perform the analysis. title: AnalysisCostModel AnalysisCost: type: object properties: type: $ref: '#/components/schemas/AnalysisCostType' description: This is the type of cost, always 'analysis' for this class. analysisType: $ref: '#/components/schemas/AnalysisCostAnalysisType' description: This is the type of analysis performed. model: $ref: '#/components/schemas/AnalysisCostModel' description: This is the model that was used to perform the analysis. promptTokens: type: number format: double description: This is the number of prompt tokens used in the analysis. completionTokens: type: number format: double description: This is the number of completion tokens generated in the analysis. cachedPromptTokens: type: number format: double description: >- This is the number of cached prompt tokens used in the analysis. This is only applicable to certain providers (e.g., OpenAI, Azure OpenAI) that support prompt caching. Cached tokens are billed at a discounted rate. cost: type: number format: double description: This is the cost of the component in USD. required: - type - analysisType - model - promptTokens - completionTokens - cost title: AnalysisCost KnowledgeBaseCostType: type: string enum: - knowledge-base description: This is the type of cost, always 'knowledge-base' for this class. title: KnowledgeBaseCostType KnowledgeBaseCostModel: type: object properties: {} description: This is the model that was used for processing the knowledge base. title: KnowledgeBaseCostModel KnowledgeBaseCost: type: object properties: type: $ref: '#/components/schemas/KnowledgeBaseCostType' description: This is the type of cost, always 'knowledge-base' for this class. model: $ref: '#/components/schemas/KnowledgeBaseCostModel' description: This is the model that was used for processing the knowledge base. promptTokens: type: number format: double description: >- This is the number of prompt tokens used in the knowledge base query. completionTokens: type: number format: double description: >- This is the number of completion tokens generated in the knowledge base query. cost: type: number format: double description: This is the cost of the component in USD. required: - type - model - promptTokens - completionTokens - cost title: KnowledgeBaseCost CallCostsItems: oneOf: - $ref: '#/components/schemas/TransportCost' - $ref: '#/components/schemas/TranscriberCost' - $ref: '#/components/schemas/ModelCost' - $ref: '#/components/schemas/VoiceCost' - $ref: '#/components/schemas/VapiCost' - $ref: '#/components/schemas/VoicemailDetectionCost' - $ref: '#/components/schemas/AnalysisCost' - $ref: '#/components/schemas/KnowledgeBaseCost' title: CallCostsItems UserMessageMetadata: type: object properties: {} description: >- The metadata associated with the message. Currently used to store the transcriber's word level confidence. title: UserMessageMetadata UserMessage: type: object properties: role: type: string description: The role of the user in the conversation. message: type: string description: The message content from the user. time: type: number format: double description: The timestamp when the message was sent. endTime: type: number format: double description: The timestamp when the message ended. secondsFromStart: type: number format: double description: The number of seconds from the start of the conversation. duration: type: number format: double description: The duration of the message in seconds. isFiltered: type: boolean description: Indicates if the message was filtered for security reasons. detectedThreats: type: array items: type: string description: List of detected security threats if the message was filtered. originalMessage: type: string description: >- The original message before filtering (only included if content was filtered). metadata: $ref: '#/components/schemas/UserMessageMetadata' description: >- The metadata associated with the message. Currently used to store the transcriber's word level confidence. speakerLabel: type: string description: Stable speaker label for diarized user speakers (e.g., "Speaker 1"). required: - role - message - time - endTime - secondsFromStart title: UserMessage SystemMessage: type: object properties: role: type: string description: The role of the system in the conversation. message: type: string description: The message content from the system. time: type: number format: double description: The timestamp when the message was sent. secondsFromStart: type: number format: double description: The number of seconds from the start of the conversation. required: - role - message - time - secondsFromStart title: SystemMessage BotMessage: type: object properties: role: type: string description: The role of the bot in the conversation. message: type: string description: The message content from the bot. time: type: number format: double description: The timestamp when the message was sent. endTime: type: number format: double description: The timestamp when the message ended. secondsFromStart: type: number format: double description: The number of seconds from the start of the conversation. source: type: string description: The source of the message. duration: type: number format: double description: The duration of the message in seconds. required: - role - message - time - endTime - secondsFromStart title: BotMessage ToolCallMessageToolCallsItems: type: object properties: {} title: ToolCallMessageToolCallsItems ToolCallMessage: type: object properties: role: type: string description: The role of the tool call in the conversation. toolCalls: type: array items: $ref: '#/components/schemas/ToolCallMessageToolCallsItems' description: The list of tool calls made during the conversation. message: type: string description: The message content for the tool call. time: type: number format: double description: The timestamp when the message was sent. secondsFromStart: type: number format: double description: The number of seconds from the start of the conversation. required: - role - toolCalls - message - time - secondsFromStart title: ToolCallMessage ToolCallResultMessageMetadata: type: object properties: {} description: The metadata for the tool call result. title: ToolCallResultMessageMetadata ToolCallResultMessage: type: object properties: role: type: string description: The role of the tool call result in the conversation. toolCallId: type: string description: The ID of the tool call. name: type: string description: The name of the tool that returned the result. result: type: string description: The result of the tool call in JSON format. time: type: number format: double description: The timestamp when the message was sent. secondsFromStart: type: number format: double description: The number of seconds from the start of the conversation. metadata: $ref: '#/components/schemas/ToolCallResultMessageMetadata' description: The metadata for the tool call result. required: - role - toolCallId - name - result - time - secondsFromStart title: ToolCallResultMessage CallMessagesItems: oneOf: - $ref: '#/components/schemas/UserMessage' - $ref: '#/components/schemas/SystemMessage' - $ref: '#/components/schemas/BotMessage' - $ref: '#/components/schemas/ToolCallMessage' - $ref: '#/components/schemas/ToolCallResultMessage' title: CallMessagesItems CallPhoneCallProvider: type: string enum: - twilio - vonage - vapi - telnyx description: |- This is the provider of the call. Only relevant for `outboundPhoneCall` and `inboundPhoneCall` type. title: CallPhoneCallProvider CallPhoneCallTransport: type: string enum: - sip - pstn description: |- This is the transport of the phone call. Only relevant for `outboundPhoneCall` and `inboundPhoneCall` type. title: CallPhoneCallTransport CallStatus: type: string enum: - scheduled - queued - ringing - in-progress - forwarding - ended - not-found - deletion-failed description: This is the status of the call. title: CallStatus CallEndedReason: type: string enum: - call-start-error-neither-assistant-nor-server-set - assistant-request-failed - assistant-request-returned-error - assistant-request-returned-unspeakable-error - assistant-request-returned-invalid-assistant - assistant-request-returned-no-assistant - assistant-request-returned-forwarding-phone-number - scheduled-call-deleted - call.start.error-vapifault-get-org - call.start.error-vapifault-get-subscription - call.start.error-get-assistant - call.start.error-get-phone-number - call.start.error-get-customer - call.start.error-get-resources-validation - call.start.error-vapi-number-international - call.start.error-vapi-number-outbound-daily-limit - call.start.error-get-transport - call.start.error-subscription-wallet-does-not-exist - call.start.error-fraud-check-failed - call.start.error-subscription-frozen - call.start.error-subscription-insufficient-credits - call.start.error-subscription-upgrade-failed - call.start.error-subscription-concurrency-limit-reached - call.start.error-enterprise-feature-not-available-recording-consent - assistant-not-valid - call.start.error-vapifault-database-error - assistant-not-found - pipeline-error-openai-voice-failed - pipeline-error-cartesia-voice-failed - pipeline-error-deepgram-voice-failed - pipeline-error-eleven-labs-voice-failed - pipeline-error-playht-voice-failed - pipeline-error-lmnt-voice-failed - pipeline-error-azure-voice-failed - pipeline-error-rime-ai-voice-failed - pipeline-error-smallest-ai-voice-failed - pipeline-error-vapi-voice-failed - pipeline-error-neuphonic-voice-failed - pipeline-error-hume-voice-failed - pipeline-error-sesame-voice-failed - pipeline-error-inworld-voice-failed - pipeline-error-minimax-voice-failed - pipeline-error-wellsaid-voice-failed - pipeline-error-tavus-video-failed - call.in-progress.error-vapifault-openai-voice-failed - call.in-progress.error-vapifault-cartesia-voice-failed - call.in-progress.error-vapifault-deepgram-voice-failed - call.in-progress.error-vapifault-eleven-labs-voice-failed - call.in-progress.error-vapifault-playht-voice-failed - call.in-progress.error-vapifault-lmnt-voice-failed - call.in-progress.error-vapifault-azure-voice-failed - call.in-progress.error-vapifault-rime-ai-voice-failed - call.in-progress.error-vapifault-smallest-ai-voice-failed - call.in-progress.error-vapifault-vapi-voice-failed - call.in-progress.error-vapifault-neuphonic-voice-failed - call.in-progress.error-vapifault-hume-voice-failed - call.in-progress.error-vapifault-sesame-voice-failed - call.in-progress.error-vapifault-inworld-voice-failed - call.in-progress.error-vapifault-minimax-voice-failed - call.in-progress.error-vapifault-wellsaid-voice-failed - call.in-progress.error-vapifault-tavus-video-failed - pipeline-error-vapi-llm-failed - pipeline-error-vapi-400-bad-request-validation-failed - pipeline-error-vapi-401-unauthorized - pipeline-error-vapi-403-model-access-denied - pipeline-error-vapi-429-exceeded-quota - pipeline-error-vapi-500-server-error - pipeline-error-vapi-503-server-overloaded-error - call.in-progress.error-providerfault-vapi-llm-failed - >- call.in-progress.error-vapifault-vapi-400-bad-request-validation-failed - call.in-progress.error-vapifault-vapi-401-unauthorized - call.in-progress.error-vapifault-vapi-403-model-access-denied - call.in-progress.error-vapifault-vapi-429-exceeded-quota - call.in-progress.error-providerfault-vapi-500-server-error - call.in-progress.error-providerfault-vapi-503-server-overloaded-error - pipeline-error-deepgram-transcriber-failed - pipeline-error-deepgram-transcriber-api-key-missing - call.in-progress.error-vapifault-deepgram-transcriber-failed - pipeline-error-gladia-transcriber-failed - call.in-progress.error-vapifault-gladia-transcriber-failed - pipeline-error-speechmatics-transcriber-failed - call.in-progress.error-vapifault-speechmatics-transcriber-failed - pipeline-error-assembly-ai-transcriber-failed - pipeline-error-assembly-ai-returning-400-insufficent-funds - pipeline-error-assembly-ai-returning-400-paid-only-feature - pipeline-error-assembly-ai-returning-401-invalid-credentials - pipeline-error-assembly-ai-returning-500-invalid-schema - pipeline-error-assembly-ai-returning-500-word-boost-parsing-failed - call.in-progress.error-vapifault-assembly-ai-transcriber-failed - >- call.in-progress.error-vapifault-assembly-ai-returning-400-insufficent-funds - >- call.in-progress.error-vapifault-assembly-ai-returning-400-paid-only-feature - >- call.in-progress.error-vapifault-assembly-ai-returning-401-invalid-credentials - >- call.in-progress.error-vapifault-assembly-ai-returning-500-invalid-schema - >- call.in-progress.error-vapifault-assembly-ai-returning-500-word-boost-parsing-failed - pipeline-error-talkscriber-transcriber-failed - call.in-progress.error-vapifault-talkscriber-transcriber-failed - pipeline-error-azure-speech-transcriber-failed - call.in-progress.error-vapifault-azure-speech-transcriber-failed - pipeline-error-eleven-labs-transcriber-failed - call.in-progress.error-vapifault-eleven-labs-transcriber-failed - pipeline-error-google-transcriber-failed - call.in-progress.error-vapifault-google-transcriber-failed - pipeline-error-openai-transcriber-failed - call.in-progress.error-vapifault-openai-transcriber-failed - pipeline-error-soniox-transcriber-auth-failed - pipeline-error-soniox-transcriber-rate-limited - pipeline-error-soniox-transcriber-invalid-config - pipeline-error-soniox-transcriber-server-error - pipeline-error-soniox-transcriber-failed - call.in-progress.error-vapifault-soniox-transcriber-auth-failed - call.in-progress.error-vapifault-soniox-transcriber-rate-limited - call.in-progress.error-vapifault-soniox-transcriber-invalid-config - call.in-progress.error-vapifault-soniox-transcriber-server-error - call.in-progress.error-vapifault-soniox-transcriber-failed - call.in-progress.error-pipeline-no-available-llm-model - worker-shutdown - vonage-disconnected - vonage-failed-to-connect-call - vonage-completed - phone-call-provider-bypass-enabled-but-no-call-received - call.in-progress.error-providerfault-transport-never-connected - call.in-progress.error-vapifault-worker-not-available - call.in-progress.error-vapifault-transport-never-connected - >- call.in-progress.error-vapifault-transport-connected-but-call-not-active - >- call.in-progress.error-vapifault-call-started-but-connection-to-transport-missing - call.in-progress.error-vapifault-worker-died - call.in-progress.twilio-completed-call - call.in-progress.sip-completed-call - call.in-progress.error-sip-inbound-call-failed-to-connect - >- call.in-progress.error-providerfault-outbound-sip-503-service-unavailable - call.in-progress.error-sip-outbound-call-failed-to-connect - call.ringing.error-sip-inbound-call-failed-to-connect - call.in-progress.error-providerfault-openai-llm-failed - call.in-progress.error-providerfault-azure-openai-llm-failed - call.in-progress.error-providerfault-groq-llm-failed - call.in-progress.error-providerfault-google-llm-failed - call.in-progress.error-providerfault-xai-llm-failed - call.in-progress.error-providerfault-mistral-llm-failed - call.in-progress.error-providerfault-minimax-llm-failed - call.in-progress.error-providerfault-inflection-ai-llm-failed - call.in-progress.error-providerfault-cerebras-llm-failed - call.in-progress.error-providerfault-deep-seek-llm-failed - call.in-progress.error-providerfault-baseten-llm-failed - call.in-progress.error-vapifault-chat-pipeline-failed-to-start - pipeline-error-openai-400-bad-request-validation-failed - pipeline-error-openai-401-unauthorized - pipeline-error-openai-401-incorrect-api-key - pipeline-error-openai-401-account-not-in-organization - pipeline-error-openai-403-model-access-denied - pipeline-error-openai-429-exceeded-quota - pipeline-error-openai-429-rate-limit-reached - pipeline-error-openai-500-server-error - pipeline-error-openai-503-server-overloaded-error - pipeline-error-openai-llm-failed - >- call.in-progress.error-vapifault-openai-400-bad-request-validation-failed - call.in-progress.error-vapifault-openai-401-unauthorized - call.in-progress.error-vapifault-openai-401-incorrect-api-key - >- call.in-progress.error-vapifault-openai-401-account-not-in-organization - call.in-progress.error-vapifault-openai-403-model-access-denied - call.in-progress.error-vapifault-openai-429-exceeded-quota - call.in-progress.error-vapifault-openai-429-rate-limit-reached - call.in-progress.error-providerfault-openai-500-server-error - >- call.in-progress.error-providerfault-openai-503-server-overloaded-error - pipeline-error-azure-openai-400-bad-request-validation-failed - pipeline-error-azure-openai-401-unauthorized - pipeline-error-azure-openai-403-model-access-denied - pipeline-error-azure-openai-429-exceeded-quota - pipeline-error-azure-openai-500-server-error - pipeline-error-azure-openai-503-server-overloaded-error - pipeline-error-azure-openai-llm-failed - >- call.in-progress.error-vapifault-azure-openai-400-bad-request-validation-failed - call.in-progress.error-vapifault-azure-openai-401-unauthorized - call.in-progress.error-vapifault-azure-openai-403-model-access-denied - call.in-progress.error-vapifault-azure-openai-429-exceeded-quota - call.in-progress.error-providerfault-azure-openai-500-server-error - >- call.in-progress.error-providerfault-azure-openai-503-server-overloaded-error - pipeline-error-google-400-bad-request-validation-failed - pipeline-error-google-401-unauthorized - pipeline-error-google-403-model-access-denied - pipeline-error-google-429-exceeded-quota - pipeline-error-google-500-server-error - pipeline-error-google-503-server-overloaded-error - pipeline-error-google-llm-failed - >- call.in-progress.error-vapifault-google-400-bad-request-validation-failed - call.in-progress.error-vapifault-google-401-unauthorized - call.in-progress.error-vapifault-google-403-model-access-denied - call.in-progress.error-vapifault-google-429-exceeded-quota - call.in-progress.error-providerfault-google-500-server-error - >- call.in-progress.error-providerfault-google-503-server-overloaded-error - pipeline-error-xai-400-bad-request-validation-failed - pipeline-error-xai-401-unauthorized - pipeline-error-xai-403-model-access-denied - pipeline-error-xai-429-exceeded-quota - pipeline-error-xai-500-server-error - pipeline-error-xai-503-server-overloaded-error - pipeline-error-xai-llm-failed - call.in-progress.error-vapifault-xai-400-bad-request-validation-failed - call.in-progress.error-vapifault-xai-401-unauthorized - call.in-progress.error-vapifault-xai-403-model-access-denied - call.in-progress.error-vapifault-xai-429-exceeded-quota - call.in-progress.error-providerfault-xai-500-server-error - call.in-progress.error-providerfault-xai-503-server-overloaded-error - pipeline-error-baseten-400-bad-request-validation-failed - pipeline-error-baseten-401-unauthorized - pipeline-error-baseten-403-model-access-denied - pipeline-error-baseten-429-exceeded-quota - pipeline-error-baseten-500-server-error - pipeline-error-baseten-503-server-overloaded-error - pipeline-error-baseten-llm-failed - >- call.in-progress.error-vapifault-baseten-400-bad-request-validation-failed - call.in-progress.error-vapifault-baseten-401-unauthorized - call.in-progress.error-vapifault-baseten-403-model-access-denied - call.in-progress.error-vapifault-baseten-429-exceeded-quota - call.in-progress.error-providerfault-baseten-500-server-error - >- call.in-progress.error-providerfault-baseten-503-server-overloaded-error - pipeline-error-mistral-400-bad-request-validation-failed - pipeline-error-mistral-401-unauthorized - pipeline-error-mistral-403-model-access-denied - pipeline-error-mistral-429-exceeded-quota - pipeline-error-mistral-500-server-error - pipeline-error-mistral-503-server-overloaded-error - pipeline-error-mistral-llm-failed - >- call.in-progress.error-vapifault-mistral-400-bad-request-validation-failed - call.in-progress.error-vapifault-mistral-401-unauthorized - call.in-progress.error-vapifault-mistral-403-model-access-denied - call.in-progress.error-vapifault-mistral-429-exceeded-quota - call.in-progress.error-providerfault-mistral-500-server-error - >- call.in-progress.error-providerfault-mistral-503-server-overloaded-error - pipeline-error-minimax-400-bad-request-validation-failed - pipeline-error-minimax-401-unauthorized - pipeline-error-minimax-403-model-access-denied - pipeline-error-minimax-429-exceeded-quota - pipeline-error-minimax-500-server-error - pipeline-error-minimax-503-server-overloaded-error - pipeline-error-minimax-llm-failed - >- call.in-progress.error-vapifault-minimax-400-bad-request-validation-failed - call.in-progress.error-vapifault-minimax-401-unauthorized - call.in-progress.error-vapifault-minimax-403-model-access-denied - call.in-progress.error-vapifault-minimax-429-exceeded-quota - call.in-progress.error-providerfault-minimax-500-server-error - >- call.in-progress.error-providerfault-minimax-503-server-overloaded-error - pipeline-error-inflection-ai-400-bad-request-validation-failed - pipeline-error-inflection-ai-401-unauthorized - pipeline-error-inflection-ai-403-model-access-denied - pipeline-error-inflection-ai-429-exceeded-quota - pipeline-error-inflection-ai-500-server-error - pipeline-error-inflection-ai-503-server-overloaded-error - pipeline-error-inflection-ai-llm-failed - >- call.in-progress.error-vapifault-inflection-ai-400-bad-request-validation-failed - call.in-progress.error-vapifault-inflection-ai-401-unauthorized - call.in-progress.error-vapifault-inflection-ai-403-model-access-denied - call.in-progress.error-vapifault-inflection-ai-429-exceeded-quota - call.in-progress.error-providerfault-inflection-ai-500-server-error - >- call.in-progress.error-providerfault-inflection-ai-503-server-overloaded-error - pipeline-error-deep-seek-400-bad-request-validation-failed - pipeline-error-deep-seek-401-unauthorized - pipeline-error-deep-seek-403-model-access-denied - pipeline-error-deep-seek-429-exceeded-quota - pipeline-error-deep-seek-500-server-error - pipeline-error-deep-seek-503-server-overloaded-error - pipeline-error-deep-seek-llm-failed - >- call.in-progress.error-vapifault-deep-seek-400-bad-request-validation-failed - call.in-progress.error-vapifault-deep-seek-401-unauthorized - call.in-progress.error-vapifault-deep-seek-403-model-access-denied - call.in-progress.error-vapifault-deep-seek-429-exceeded-quota - call.in-progress.error-providerfault-deep-seek-500-server-error - >- call.in-progress.error-providerfault-deep-seek-503-server-overloaded-error - pipeline-error-groq-400-bad-request-validation-failed - pipeline-error-groq-401-unauthorized - pipeline-error-groq-403-model-access-denied - pipeline-error-groq-429-exceeded-quota - pipeline-error-groq-500-server-error - pipeline-error-groq-503-server-overloaded-error - pipeline-error-groq-llm-failed - >- call.in-progress.error-vapifault-groq-400-bad-request-validation-failed - call.in-progress.error-vapifault-groq-401-unauthorized - call.in-progress.error-vapifault-groq-403-model-access-denied - call.in-progress.error-vapifault-groq-429-exceeded-quota - call.in-progress.error-providerfault-groq-500-server-error - call.in-progress.error-providerfault-groq-503-server-overloaded-error - pipeline-error-cerebras-400-bad-request-validation-failed - pipeline-error-cerebras-401-unauthorized - pipeline-error-cerebras-403-model-access-denied - pipeline-error-cerebras-429-exceeded-quota - pipeline-error-cerebras-500-server-error - pipeline-error-cerebras-503-server-overloaded-error - pipeline-error-cerebras-llm-failed - >- call.in-progress.error-vapifault-cerebras-400-bad-request-validation-failed - call.in-progress.error-vapifault-cerebras-401-unauthorized - call.in-progress.error-vapifault-cerebras-403-model-access-denied - call.in-progress.error-vapifault-cerebras-429-exceeded-quota - call.in-progress.error-providerfault-cerebras-500-server-error - >- call.in-progress.error-providerfault-cerebras-503-server-overloaded-error - pipeline-error-anthropic-400-bad-request-validation-failed - pipeline-error-anthropic-401-unauthorized - pipeline-error-anthropic-403-model-access-denied - pipeline-error-anthropic-429-exceeded-quota - pipeline-error-anthropic-500-server-error - pipeline-error-anthropic-503-server-overloaded-error - pipeline-error-anthropic-llm-failed - call.in-progress.error-providerfault-anthropic-llm-failed - >- call.in-progress.error-vapifault-anthropic-400-bad-request-validation-failed - call.in-progress.error-vapifault-anthropic-401-unauthorized - call.in-progress.error-vapifault-anthropic-403-model-access-denied - call.in-progress.error-vapifault-anthropic-429-exceeded-quota - call.in-progress.error-providerfault-anthropic-500-server-error - >- call.in-progress.error-providerfault-anthropic-503-server-overloaded-error - pipeline-error-anthropic-bedrock-400-bad-request-validation-failed - pipeline-error-anthropic-bedrock-401-unauthorized - pipeline-error-anthropic-bedrock-403-model-access-denied - pipeline-error-anthropic-bedrock-429-exceeded-quota - pipeline-error-anthropic-bedrock-500-server-error - pipeline-error-anthropic-bedrock-503-server-overloaded-error - pipeline-error-anthropic-bedrock-llm-failed - call.in-progress.error-providerfault-anthropic-bedrock-llm-failed - >- call.in-progress.error-vapifault-anthropic-bedrock-400-bad-request-validation-failed - call.in-progress.error-vapifault-anthropic-bedrock-401-unauthorized - >- call.in-progress.error-vapifault-anthropic-bedrock-403-model-access-denied - call.in-progress.error-vapifault-anthropic-bedrock-429-exceeded-quota - >- call.in-progress.error-providerfault-anthropic-bedrock-500-server-error - >- call.in-progress.error-providerfault-anthropic-bedrock-503-server-overloaded-error - pipeline-error-anthropic-vertex-400-bad-request-validation-failed - pipeline-error-anthropic-vertex-401-unauthorized - pipeline-error-anthropic-vertex-403-model-access-denied - pipeline-error-anthropic-vertex-429-exceeded-quota - pipeline-error-anthropic-vertex-500-server-error - pipeline-error-anthropic-vertex-503-server-overloaded-error - pipeline-error-anthropic-vertex-llm-failed - call.in-progress.error-providerfault-anthropic-vertex-llm-failed - >- call.in-progress.error-vapifault-anthropic-vertex-400-bad-request-validation-failed - call.in-progress.error-vapifault-anthropic-vertex-401-unauthorized - >- call.in-progress.error-vapifault-anthropic-vertex-403-model-access-denied - call.in-progress.error-vapifault-anthropic-vertex-429-exceeded-quota - call.in-progress.error-providerfault-anthropic-vertex-500-server-error - >- call.in-progress.error-providerfault-anthropic-vertex-503-server-overloaded-error - pipeline-error-together-ai-400-bad-request-validation-failed - pipeline-error-together-ai-401-unauthorized - pipeline-error-together-ai-403-model-access-denied - pipeline-error-together-ai-429-exceeded-quota - pipeline-error-together-ai-500-server-error - pipeline-error-together-ai-503-server-overloaded-error - pipeline-error-together-ai-llm-failed - call.in-progress.error-providerfault-together-ai-llm-failed - >- call.in-progress.error-vapifault-together-ai-400-bad-request-validation-failed - call.in-progress.error-vapifault-together-ai-401-unauthorized - call.in-progress.error-vapifault-together-ai-403-model-access-denied - call.in-progress.error-vapifault-together-ai-429-exceeded-quota - call.in-progress.error-providerfault-together-ai-500-server-error - >- call.in-progress.error-providerfault-together-ai-503-server-overloaded-error - pipeline-error-anyscale-400-bad-request-validation-failed - pipeline-error-anyscale-401-unauthorized - pipeline-error-anyscale-403-model-access-denied - pipeline-error-anyscale-429-exceeded-quota - pipeline-error-anyscale-500-server-error - pipeline-error-anyscale-503-server-overloaded-error - pipeline-error-anyscale-llm-failed - call.in-progress.error-providerfault-anyscale-llm-failed - >- call.in-progress.error-vapifault-anyscale-400-bad-request-validation-failed - call.in-progress.error-vapifault-anyscale-401-unauthorized - call.in-progress.error-vapifault-anyscale-403-model-access-denied - call.in-progress.error-vapifault-anyscale-429-exceeded-quota - call.in-progress.error-providerfault-anyscale-500-server-error - >- call.in-progress.error-providerfault-anyscale-503-server-overloaded-error - pipeline-error-openrouter-400-bad-request-validation-failed - pipeline-error-openrouter-401-unauthorized - pipeline-error-openrouter-403-model-access-denied - pipeline-error-openrouter-429-exceeded-quota - pipeline-error-openrouter-500-server-error - pipeline-error-openrouter-503-server-overloaded-error - pipeline-error-openrouter-llm-failed - call.in-progress.error-providerfault-openrouter-llm-failed - >- call.in-progress.error-vapifault-openrouter-400-bad-request-validation-failed - call.in-progress.error-vapifault-openrouter-401-unauthorized - call.in-progress.error-vapifault-openrouter-403-model-access-denied - call.in-progress.error-vapifault-openrouter-429-exceeded-quota - call.in-progress.error-providerfault-openrouter-500-server-error - >- call.in-progress.error-providerfault-openrouter-503-server-overloaded-error - pipeline-error-perplexity-ai-400-bad-request-validation-failed - pipeline-error-perplexity-ai-401-unauthorized - pipeline-error-perplexity-ai-403-model-access-denied - pipeline-error-perplexity-ai-429-exceeded-quota - pipeline-error-perplexity-ai-500-server-error - pipeline-error-perplexity-ai-503-server-overloaded-error - pipeline-error-perplexity-ai-llm-failed - call.in-progress.error-providerfault-perplexity-ai-llm-failed - >- call.in-progress.error-vapifault-perplexity-ai-400-bad-request-validation-failed - call.in-progress.error-vapifault-perplexity-ai-401-unauthorized - call.in-progress.error-vapifault-perplexity-ai-403-model-access-denied - call.in-progress.error-vapifault-perplexity-ai-429-exceeded-quota - call.in-progress.error-providerfault-perplexity-ai-500-server-error - >- call.in-progress.error-providerfault-perplexity-ai-503-server-overloaded-error - pipeline-error-deepinfra-400-bad-request-validation-failed - pipeline-error-deepinfra-401-unauthorized - pipeline-error-deepinfra-403-model-access-denied - pipeline-error-deepinfra-429-exceeded-quota - pipeline-error-deepinfra-500-server-error - pipeline-error-deepinfra-503-server-overloaded-error - pipeline-error-deepinfra-llm-failed - call.in-progress.error-providerfault-deepinfra-llm-failed - >- call.in-progress.error-vapifault-deepinfra-400-bad-request-validation-failed - call.in-progress.error-vapifault-deepinfra-401-unauthorized - call.in-progress.error-vapifault-deepinfra-403-model-access-denied - call.in-progress.error-vapifault-deepinfra-429-exceeded-quota - call.in-progress.error-providerfault-deepinfra-500-server-error - >- call.in-progress.error-providerfault-deepinfra-503-server-overloaded-error - pipeline-error-runpod-400-bad-request-validation-failed - pipeline-error-runpod-401-unauthorized - pipeline-error-runpod-403-model-access-denied - pipeline-error-runpod-429-exceeded-quota - pipeline-error-runpod-500-server-error - pipeline-error-runpod-503-server-overloaded-error - pipeline-error-runpod-llm-failed - call.in-progress.error-providerfault-runpod-llm-failed - >- call.in-progress.error-vapifault-runpod-400-bad-request-validation-failed - call.in-progress.error-vapifault-runpod-401-unauthorized - call.in-progress.error-vapifault-runpod-403-model-access-denied - call.in-progress.error-vapifault-runpod-429-exceeded-quota - call.in-progress.error-providerfault-runpod-500-server-error - >- call.in-progress.error-providerfault-runpod-503-server-overloaded-error - pipeline-error-custom-llm-400-bad-request-validation-failed - pipeline-error-custom-llm-401-unauthorized - pipeline-error-custom-llm-403-model-access-denied - pipeline-error-custom-llm-429-exceeded-quota - pipeline-error-custom-llm-500-server-error - pipeline-error-custom-llm-503-server-overloaded-error - pipeline-error-custom-llm-llm-failed - call.in-progress.error-providerfault-custom-llm-llm-failed - >- call.in-progress.error-vapifault-custom-llm-400-bad-request-validation-failed - call.in-progress.error-vapifault-custom-llm-401-unauthorized - call.in-progress.error-vapifault-custom-llm-403-model-access-denied - call.in-progress.error-vapifault-custom-llm-429-exceeded-quota - call.in-progress.error-providerfault-custom-llm-500-server-error - >- call.in-progress.error-providerfault-custom-llm-503-server-overloaded-error - call.in-progress.error-pipeline-ws-model-connection-failed - pipeline-error-custom-voice-failed - pipeline-error-cartesia-socket-hang-up - pipeline-error-cartesia-requested-payment - pipeline-error-cartesia-500-server-error - pipeline-error-cartesia-502-server-error - pipeline-error-cartesia-503-server-error - pipeline-error-cartesia-522-server-error - call.in-progress.error-vapifault-cartesia-socket-hang-up - call.in-progress.error-vapifault-cartesia-requested-payment - call.in-progress.error-providerfault-cartesia-500-server-error - call.in-progress.error-providerfault-cartesia-503-server-error - call.in-progress.error-providerfault-cartesia-522-server-error - pipeline-error-eleven-labs-voice-not-found - pipeline-error-eleven-labs-quota-exceeded - pipeline-error-eleven-labs-unauthorized-access - pipeline-error-eleven-labs-unauthorized-to-access-model - pipeline-error-eleven-labs-professional-voices-only-for-creator-plus - pipeline-error-eleven-labs-blocked-free-plan-and-requested-upgrade - >- pipeline-error-eleven-labs-blocked-concurrent-requests-and-requested-upgrade - >- pipeline-error-eleven-labs-blocked-using-instant-voice-clone-and-requested-upgrade - pipeline-error-eleven-labs-system-busy-and-requested-upgrade - pipeline-error-eleven-labs-voice-not-fine-tuned - pipeline-error-eleven-labs-invalid-api-key - pipeline-error-eleven-labs-invalid-voice-samples - pipeline-error-eleven-labs-voice-disabled-by-owner - pipeline-error-eleven-labs-vapi-voice-disabled-by-owner - pipeline-error-eleven-labs-blocked-account-in-probation - pipeline-error-eleven-labs-blocked-content-against-their-policy - pipeline-error-eleven-labs-missing-samples-for-voice-clone - pipeline-error-eleven-labs-voice-not-fine-tuned-and-cannot-be-used - pipeline-error-eleven-labs-voice-not-allowed-for-free-users - pipeline-error-eleven-labs-max-character-limit-exceeded - >- pipeline-error-eleven-labs-blocked-voice-potentially-against-terms-of-service-and-awaiting-verification - pipeline-error-eleven-labs-500-server-error - pipeline-error-eleven-labs-503-server-error - call.in-progress.error-vapifault-eleven-labs-voice-not-found - call.in-progress.error-vapifault-eleven-labs-quota-exceeded - call.in-progress.error-vapifault-eleven-labs-unauthorized-access - >- call.in-progress.error-vapifault-eleven-labs-unauthorized-to-access-model - >- call.in-progress.error-vapifault-eleven-labs-professional-voices-only-for-creator-plus - >- call.in-progress.error-vapifault-eleven-labs-blocked-free-plan-and-requested-upgrade - >- call.in-progress.error-vapifault-eleven-labs-blocked-concurrent-requests-and-requested-upgrade - >- call.in-progress.error-vapifault-eleven-labs-blocked-using-instant-voice-clone-and-requested-upgrade - >- call.in-progress.error-vapifault-eleven-labs-system-busy-and-requested-upgrade - call.in-progress.error-vapifault-eleven-labs-voice-not-fine-tuned - call.in-progress.error-vapifault-eleven-labs-invalid-api-key - call.in-progress.error-vapifault-eleven-labs-invalid-voice-samples - call.in-progress.error-vapifault-eleven-labs-voice-disabled-by-owner - >- call.in-progress.error-vapifault-eleven-labs-blocked-account-in-probation - >- call.in-progress.error-vapifault-eleven-labs-blocked-content-against-their-policy - >- call.in-progress.error-vapifault-eleven-labs-missing-samples-for-voice-clone - >- call.in-progress.error-vapifault-eleven-labs-voice-not-fine-tuned-and-cannot-be-used - >- call.in-progress.error-vapifault-eleven-labs-voice-not-allowed-for-free-users - >- call.in-progress.error-vapifault-eleven-labs-max-character-limit-exceeded - >- call.in-progress.error-vapifault-eleven-labs-blocked-voice-potentially-against-terms-of-service-and-awaiting-verification - >- call.in-progress.error-providerfault-eleven-labs-system-busy-and-requested-upgrade - call.in-progress.error-providerfault-eleven-labs-500-server-error - call.in-progress.error-providerfault-eleven-labs-503-server-error - pipeline-error-playht-request-timed-out - pipeline-error-playht-invalid-voice - pipeline-error-playht-unexpected-error - pipeline-error-playht-out-of-credits - pipeline-error-playht-invalid-emotion - pipeline-error-playht-voice-must-be-a-valid-voice-manifest-uri - pipeline-error-playht-401-unauthorized - pipeline-error-playht-403-forbidden-out-of-characters - pipeline-error-playht-403-forbidden-api-access-not-available - pipeline-error-playht-429-exceeded-quota - pipeline-error-playht-502-gateway-error - pipeline-error-playht-504-gateway-error - call.in-progress.error-vapifault-playht-request-timed-out - call.in-progress.error-vapifault-playht-invalid-voice - call.in-progress.error-vapifault-playht-unexpected-error - call.in-progress.error-vapifault-playht-out-of-credits - call.in-progress.error-vapifault-playht-invalid-emotion - >- call.in-progress.error-vapifault-playht-voice-must-be-a-valid-voice-manifest-uri - call.in-progress.error-vapifault-playht-401-unauthorized - >- call.in-progress.error-vapifault-playht-403-forbidden-out-of-characters - >- call.in-progress.error-vapifault-playht-403-forbidden-api-access-not-available - call.in-progress.error-vapifault-playht-429-exceeded-quota - call.in-progress.error-providerfault-playht-502-gateway-error - call.in-progress.error-providerfault-playht-504-gateway-error - pipeline-error-custom-transcriber-failed - call.in-progress.error-vapifault-custom-transcriber-failed - pipeline-error-eleven-labs-transcriber-failed - call.in-progress.error-vapifault-eleven-labs-transcriber-failed - >- pipeline-error-deepgram-returning-400-no-such-model-language-tier-combination - pipeline-error-deepgram-returning-401-invalid-credentials - pipeline-error-deepgram-returning-403-model-access-denied - pipeline-error-deepgram-returning-404-not-found - pipeline-error-deepgram-returning-500-invalid-json - pipeline-error-deepgram-returning-502-network-error - pipeline-error-deepgram-returning-502-bad-gateway-ehostunreach - pipeline-error-deepgram-returning-econnreset - >- call.in-progress.error-vapifault-deepgram-returning-400-no-such-model-language-tier-combination - >- call.in-progress.error-vapifault-deepgram-returning-401-invalid-credentials - call.in-progress.error-vapifault-deepgram-returning-404-not-found - >- call.in-progress.error-vapifault-deepgram-returning-403-model-access-denied - >- call.in-progress.error-providerfault-deepgram-returning-500-invalid-json - >- call.in-progress.error-providerfault-deepgram-returning-502-network-error - >- call.in-progress.error-providerfault-deepgram-returning-502-bad-gateway-ehostunreach - pipeline-error-google-transcriber-failed - call.in-progress.error-vapifault-google-transcriber-failed - pipeline-error-openai-transcriber-failed - call.in-progress.error-vapifault-openai-transcriber-failed - pipeline-error-soniox-transcriber-auth-failed - pipeline-error-soniox-transcriber-rate-limited - pipeline-error-soniox-transcriber-invalid-config - pipeline-error-soniox-transcriber-server-error - pipeline-error-soniox-transcriber-failed - call.in-progress.error-vapifault-soniox-transcriber-auth-failed - call.in-progress.error-vapifault-soniox-transcriber-rate-limited - call.in-progress.error-vapifault-soniox-transcriber-invalid-config - call.in-progress.error-vapifault-soniox-transcriber-server-error - call.in-progress.error-vapifault-soniox-transcriber-failed - call.in-progress.error-warm-transfer-max-duration - call.in-progress.error-warm-transfer-assistant-cancelled - call.in-progress.error-warm-transfer-silence-timeout - call.in-progress.error-warm-transfer-microphone-timeout - assistant-ended-call - assistant-said-end-call-phrase - assistant-ended-call-with-hangup-task - assistant-ended-call-after-message-spoken - assistant-forwarded-call - assistant-join-timed-out - call.in-progress.error-assistant-did-not-receive-customer-audio - call.in-progress.error-transfer-failed - customer-busy - customer-ended-call - customer-ended-call-before-warm-transfer - customer-ended-call-after-warm-transfer-attempt - customer-ended-call-during-transfer - customer-did-not-answer - customer-did-not-give-microphone-permission - exceeded-max-duration - manually-canceled - phone-call-provider-closed-websocket - call.forwarding.operator-busy - silence-timed-out - call.in-progress.error-sip-inbound-call-failed-to-connect - call.in-progress.error-providerfault-outbound-sip-403-forbidden - >- call.in-progress.error-providerfault-outbound-sip-407-proxy-authentication-required - call.in-progress.error-providerfault-outbound-sip-408-request-timeout - >- call.in-progress.error-providerfault-outbound-sip-503-service-unavailable - >- call.in-progress.error-providerfault-outbound-sip-480-temporarily-unavailable - call.in-progress.error-sip-outbound-call-failed-to-connect - call.ringing.hook-executed-say - call.ringing.hook-executed-transfer - call.ending.hook-executed-say - call.ending.hook-executed-transfer - call.ringing.sip-inbound-caller-hungup-before-call-connect - call.ringing.error-sip-inbound-call-failed-to-connect - twilio-failed-to-connect-call - twilio-reported-customer-misdialed - vonage-rejected - voicemail - call-deleted description: This is the explanation for how the call ended. title: CallEndedReason TextContentType: type: string enum: - text title: TextContentType TextContentLanguage: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu title: TextContentLanguage TextContent: type: object properties: type: $ref: '#/components/schemas/TextContentType' text: type: string language: $ref: '#/components/schemas/TextContentLanguage' required: - type - text - language title: TextContent CustomMessageContentsItems: oneOf: - $ref: '#/components/schemas/TextContent' title: CustomMessageContentsItems CustomMessageType: type: string enum: - custom-message description: This is a custom message. title: CustomMessageType CustomMessage: type: object properties: contents: type: array items: $ref: '#/components/schemas/CustomMessageContentsItems' description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/CustomMessageType' description: This is a custom message. content: type: string description: >- This is the content that the assistant will say when this message is triggered. required: - type title: CustomMessage TransferDestinationNumberMessage: oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. title: TransferDestinationNumberMessage TransferDestinationNumberType: type: string enum: - number title: TransferDestinationNumberType TransferPlanMode: type: string enum: - blind-transfer - blind-transfer-add-summary-to-sip-header - warm-transfer-say-message - warm-transfer-say-summary - warm-transfer-twiml - warm-transfer-wait-for-operator-to-speak-first-and-then-say-message - warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary - warm-transfer-experimental description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Usage: - `blind-transfer`: The assistant forwards the call to the destination without any message or summary. - `blind-transfer-add-summary-to-sip-header`: The assistant forwards the call to the destination and adds a SIP header X-Transfer-Summary to the call to include the summary. - `warm-transfer-say-message`: The assistant dials the destination, delivers the `message` to the destination party, connects the customer, and leaves the call. - `warm-transfer-say-summary`: The assistant dials the destination, provides a summary of the call to the destination party, connects the customer, and leaves the call. - `warm-transfer-wait-for-operator-to-speak-first-and-then-say-message`: The assistant dials the destination, waits for the operator to speak, delivers the `message` to the destination party, and then connects the customer. - `warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary`: The assistant dials the destination, waits for the operator to speak, provides a summary of the call to the destination party, and then connects the customer. - `warm-transfer-twiml`: The assistant dials the destination, executes the twiml instructions on the destination call leg, connects the customer, and leaves the call. - `warm-transfer-experimental`: The assistant puts the customer on hold, dials the destination, and if the destination answers (and is human), delivers a message or summary before connecting the customer. If the destination is unreachable or not human (e.g., with voicemail detection), the assistant delivers the `fallbackMessage` to the customer and optionally ends the call. @default 'blind-transfer' title: TransferPlanMode TransferPlanMessage: oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' description: >- This is the message the assistant will deliver to the destination party before connecting the customer. Usage: - Used only when `mode` is `blind-transfer-add-summary-to-sip-header`, `warm-transfer-say-message`, `warm-transfer-wait-for-operator-to-speak-first-and-then-say-message`, or `warm-transfer-experimental`. title: TransferPlanMessage TransferPlanSipVerb: type: string enum: - refer - bye - dial default: refer description: |- This specifies the SIP verb to use while transferring the call. - 'refer': Uses SIP REFER to transfer the call (default) - 'bye': Ends current call with SIP BYE - 'dial': Uses SIP DIAL to transfer the call title: TransferPlanSipVerb ContextEngineeringPlanLastNMessagesType: type: string enum: - lastNMessages title: ContextEngineeringPlanLastNMessagesType ContextEngineeringPlanLastNMessages: type: object properties: type: $ref: '#/components/schemas/ContextEngineeringPlanLastNMessagesType' maxMessages: type: number format: double description: >- This is the maximum number of messages to include in the context engineering plan. required: - type - maxMessages title: ContextEngineeringPlanLastNMessages ContextEngineeringPlanNoneType: type: string enum: - none title: ContextEngineeringPlanNoneType ContextEngineeringPlanNone: type: object properties: type: $ref: '#/components/schemas/ContextEngineeringPlanNoneType' required: - type title: ContextEngineeringPlanNone ContextEngineeringPlanAllType: type: string enum: - all title: ContextEngineeringPlanAllType ContextEngineeringPlanAll: type: object properties: type: $ref: '#/components/schemas/ContextEngineeringPlanAllType' required: - type title: ContextEngineeringPlanAll TransferPlanContextEngineeringPlan: oneOf: - $ref: '#/components/schemas/ContextEngineeringPlanLastNMessages' - $ref: '#/components/schemas/ContextEngineeringPlanNone' - $ref: '#/components/schemas/ContextEngineeringPlanAll' description: >- This is the plan for manipulating the message context before initiating the warm transfer. Usage: - Used only when `mode` is `warm-transfer-experimental`. - These messages will automatically be added to the transferAssistant's system message. - If 'none', we will not add any transcript to the transferAssistant's system message. - If you want to provide your own messages, use transferAssistant.model.messages instead. @default { type: 'all' } title: TransferPlanContextEngineeringPlan SummaryPlanMessagesItems: type: object properties: {} title: SummaryPlanMessagesItems SummaryPlan: type: object properties: messages: type: array items: $ref: '#/components/schemas/SummaryPlanMessagesItems' description: >- These are the messages used to generate the summary. @default: ``` [ { "role": "system", "content": "You are an expert note-taker. You will be given a transcript of a call. Summarize the call in 2-3 sentences. DO NOT return anything except the summary." }, { "role": "user", "content": "Here is the transcript:\n\n{{transcript}}\n\n. Here is the ended reason of the call:\n\n{{endedReason}}\n\n" } ]``` You can customize by providing any messages you want. Here are the template variables available: - {{transcript}}: The transcript of the call from `call.artifact.transcript` - {{systemPrompt}}: The system prompt of the call from `assistant.model.messages[type=system].content` - {{messages}}: The messages of the call from `assistant.model.messages` - {{endedReason}}: The ended reason of the call from `call.endedReason` enabled: type: boolean description: >- This determines whether a summary is generated and stored in `call.analysis.summary`. Defaults to true. Usage: - If you want to disable the summary, set this to false. @default true timeoutSeconds: type: number format: double description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.summary` will be empty. Usage: - To guarantee the summary is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds title: SummaryPlan TransferFallbackPlanMessage: oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' description: >- This is the message the assistant will deliver to the customer if the transfer fails. title: TransferFallbackPlanMessage TransferFallbackPlan: type: object properties: message: $ref: '#/components/schemas/TransferFallbackPlanMessage' description: >- This is the message the assistant will deliver to the customer if the transfer fails. endCallEnabled: type: boolean default: true description: >- This controls what happens after delivering the failure message to the customer. - true: End the call after delivering the failure message (default) - false: Keep the assistant on the call to continue handling the customer's request @default true required: - message title: TransferFallbackPlan TransferPlan: type: object properties: mode: $ref: '#/components/schemas/TransferPlanMode' description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Usage: - `blind-transfer`: The assistant forwards the call to the destination without any message or summary. - `blind-transfer-add-summary-to-sip-header`: The assistant forwards the call to the destination and adds a SIP header X-Transfer-Summary to the call to include the summary. - `warm-transfer-say-message`: The assistant dials the destination, delivers the `message` to the destination party, connects the customer, and leaves the call. - `warm-transfer-say-summary`: The assistant dials the destination, provides a summary of the call to the destination party, connects the customer, and leaves the call. - `warm-transfer-wait-for-operator-to-speak-first-and-then-say-message`: The assistant dials the destination, waits for the operator to speak, delivers the `message` to the destination party, and then connects the customer. - `warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary`: The assistant dials the destination, waits for the operator to speak, provides a summary of the call to the destination party, and then connects the customer. - `warm-transfer-twiml`: The assistant dials the destination, executes the twiml instructions on the destination call leg, connects the customer, and leaves the call. - `warm-transfer-experimental`: The assistant puts the customer on hold, dials the destination, and if the destination answers (and is human), delivers a message or summary before connecting the customer. If the destination is unreachable or not human (e.g., with voicemail detection), the assistant delivers the `fallbackMessage` to the customer and optionally ends the call. @default 'blind-transfer' message: $ref: '#/components/schemas/TransferPlanMessage' description: >- This is the message the assistant will deliver to the destination party before connecting the customer. Usage: - Used only when `mode` is `blind-transfer-add-summary-to-sip-header`, `warm-transfer-say-message`, `warm-transfer-wait-for-operator-to-speak-first-and-then-say-message`, or `warm-transfer-experimental`. timeout: type: number format: double default: 60 description: >- This is the timeout in seconds for the warm-transfer-wait-for-operator-to-speak-first-and-then-say-message/summary @default 60 sipVerb: $ref: '#/components/schemas/TransferPlanSipVerb' description: |- This specifies the SIP verb to use while transferring the call. - 'refer': Uses SIP REFER to transfer the call (default) - 'bye': Ends current call with SIP BYE - 'dial': Uses SIP DIAL to transfer the call dialTimeout: type: number format: double default: 60 description: >- This sets the timeout for the dial operation in seconds. This is the duration the call will ring before timing out. Only applicable when `sipVerb='dial'`. Not applicable for SIP REFER or BYE. @default 60 holdAudioUrl: type: string description: >- This is the URL to an audio file played while the customer is on hold during transfer. Usage: - Used only when `mode` is `warm-transfer-experimental`. - Used when transferring calls to play hold audio for the customer. - Must be a publicly accessible URL to an audio file. - Supported formats: MP3 and WAV. - If not provided, the default hold audio will be used. transferCompleteAudioUrl: type: string description: >- This is the URL to an audio file played after the warm transfer message or summary is delivered to the destination party. It can be used to play a custom sound like 'beep' to notify that the transfer is complete. Usage: - Used only when `mode` is `warm-transfer-experimental`. - Used when transferring calls to play hold audio for the destination party. - Must be a publicly accessible URL to an audio file. - Supported formats: MP3 and WAV. contextEngineeringPlan: $ref: '#/components/schemas/TransferPlanContextEngineeringPlan' description: >- This is the plan for manipulating the message context before initiating the warm transfer. Usage: - Used only when `mode` is `warm-transfer-experimental`. - These messages will automatically be added to the transferAssistant's system message. - If 'none', we will not add any transcript to the transferAssistant's system message. - If you want to provide your own messages, use transferAssistant.model.messages instead. @default { type: 'all' } twiml: type: string description: >- This is the TwiML instructions to execute on the destination call leg before connecting the customer. Usage: - Used only when `mode` is `warm-transfer-twiml`. - Supports only `Play`, `Say`, `Gather`, `Hangup` and `Pause` verbs. - Maximum length is 4096 characters. Example: ``` Hello, transferring a customer to you. They called about billing questions. ``` summaryPlan: $ref: '#/components/schemas/SummaryPlan' description: >- This is the plan for generating a summary of the call to present to the destination party. Usage: - Used only when `mode` is `blind-transfer-add-summary-to-sip-header` or `warm-transfer-say-summary` or `warm-transfer-wait-for-operator-to-speak-first-and-then-say-summary` or `warm-transfer-experimental`. sipHeadersInReferToEnabled: type: boolean description: >- This flag includes the sipHeaders from above in the refer to sip uri as url encoded query params. @default false fallbackPlan: $ref: '#/components/schemas/TransferFallbackPlan' description: >- This configures the fallback plan when the transfer fails (destination unreachable, busy, or not human). Usage: - Used only when `mode` is `warm-transfer-experimental`. - If not provided when using `warm-transfer-experimental`, a default message will be used. required: - mode title: TransferPlan TransferDestinationNumber: type: object properties: message: $ref: '#/components/schemas/TransferDestinationNumberMessage' description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. type: $ref: '#/components/schemas/TransferDestinationNumberType' numberE164CheckEnabled: type: boolean default: true description: >- This is the flag to toggle the E164 check for the `number` field. This is an advanced property which should be used if you know your use case requires it. Use cases: - `false`: To allow non-E164 numbers like `+001234567890`, `1234`, or `abc`. This is useful for dialing out to non-E164 numbers on your SIP trunks. - `true` (default): To allow only E164 numbers like `+14155551234`. This is standard for PSTN calls. If `false`, the `number` is still required to only contain alphanumeric characters (regex: `/^\+?[a-zA-Z0-9]+$/`). @default true (E164 check is enabled) number: type: string description: This is the phone number to transfer the call to. extension: type: string description: >- This is the extension to dial after transferring the call to the `number`. callerId: type: string description: >- This is the caller ID to use when transferring the call to the `number`. Usage: - If not provided, the caller ID will be the number the call is coming **from**. Example: a customer with number +14151111111 calls in to and the assistant transfers out to +16470000000. +16470000000 will see +14151111111 as the caller. For inbound calls, the caller ID is the customer's number. For outbound calls, the caller ID is the phone number of the assistant. - To change this behavior, provide a `callerId`. - Set to '{{customer.number}}' to always use the customer's number as the caller ID. - Set to '{{phoneNumber.number}}' to always use the phone number of the assistant as the caller ID. - Set to any E164 number to always use that number as the caller ID. This needs to be a number that is owned or verified by your Transport provider like Twilio. For Twilio, you can read up more here: https://www.twilio.com/docs/voice/twiml/dial#callerid transferPlan: $ref: '#/components/schemas/TransferPlan' description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Defaults to `blind-transfer`. @default `transferPlan.mode='blind-transfer'` description: type: string description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. required: - type - number title: TransferDestinationNumber TransferDestinationSipMessage: oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. title: TransferDestinationSipMessage TransferDestinationSipType: type: string enum: - sip title: TransferDestinationSipType TransferDestinationSipSipHeaders: type: object properties: {} description: These are custom headers to be added to SIP refer during transfer call. title: TransferDestinationSipSipHeaders TransferDestinationSip: type: object properties: message: $ref: '#/components/schemas/TransferDestinationSipMessage' description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. type: $ref: '#/components/schemas/TransferDestinationSipType' sipUri: type: string description: This is the SIP URI to transfer the call to. callerId: type: string description: >- This is the caller ID to use when transferring the call to the `sipUri`. Usage: - If not provided, the caller ID will be determined by the SIP infrastructure. - Set to '{{customer.number}}' to always use the customer's number as the caller ID. - Set to '{{phoneNumber.number}}' to always use the phone number of the assistant as the caller ID. - Set to any E164 number to always use that number as the caller ID. Only applicable when `transferPlan.sipVerb='dial'`. Not applicable for SIP REFER. transferPlan: $ref: '#/components/schemas/TransferPlan' description: >- This configures how transfer is executed and the experience of the destination party receiving the call. Defaults to `blind-transfer`. @default `transferPlan.mode='blind-transfer'` sipHeaders: $ref: '#/components/schemas/TransferDestinationSipSipHeaders' description: >- These are custom headers to be added to SIP refer during transfer call. description: type: string description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. required: - type - sipUri title: TransferDestinationSip CallDestination: oneOf: - $ref: '#/components/schemas/TransferDestinationNumber' - $ref: '#/components/schemas/TransferDestinationSip' description: >- This is the destination where the call ended up being transferred to. If the call was not transferred, this will be empty. title: CallDestination AnalysisCostBreakdown: type: object properties: summary: type: number format: double description: This is the cost to summarize the call. summaryPromptTokens: type: number format: double description: This is the number of prompt tokens used to summarize the call. summaryCompletionTokens: type: number format: double description: This is the number of completion tokens used to summarize the call. summaryCachedPromptTokens: type: number format: double description: >- This is the number of cached prompt tokens used to summarize the call. structuredData: type: number format: double description: This is the cost to extract structured data from the call. structuredDataPromptTokens: type: number format: double description: >- This is the number of prompt tokens used to extract structured data from the call. structuredDataCompletionTokens: type: number format: double description: >- This is the number of completion tokens used to extract structured data from the call. structuredDataCachedPromptTokens: type: number format: double description: >- This is the number of cached prompt tokens used to extract structured data from the call. successEvaluation: type: number format: double description: This is the cost to evaluate if the call was successful. successEvaluationPromptTokens: type: number format: double description: >- This is the number of prompt tokens used to evaluate if the call was successful. successEvaluationCompletionTokens: type: number format: double description: >- This is the number of completion tokens used to evaluate if the call was successful. successEvaluationCachedPromptTokens: type: number format: double description: >- This is the number of cached prompt tokens used to evaluate if the call was successful. structuredOutput: type: number format: double description: This is the cost to evaluate structuredOutputs from the call. structuredOutputPromptTokens: type: number format: double description: >- This is the number of prompt tokens used to evaluate structuredOutputs from the call. structuredOutputCompletionTokens: type: number format: double description: >- This is the number of completion tokens used to evaluate structuredOutputs from the call. structuredOutputCachedPromptTokens: type: number format: double description: >- This is the number of cached prompt tokens used to evaluate structuredOutputs from the call. title: AnalysisCostBreakdown CostBreakdown: type: object properties: transport: type: number format: double description: This is the cost of the transport provider, like Twilio or Vonage. stt: type: number format: double description: This is the cost of the speech-to-text service. llm: type: number format: double description: This is the cost of the language model. tts: type: number format: double description: This is the cost of the text-to-speech service. vapi: type: number format: double description: This is the cost of Vapi. chat: type: number format: double description: This is the cost of chat interactions. total: type: number format: double description: This is the total cost of the call. llmPromptTokens: type: number format: double description: This is the LLM prompt tokens used for the call. llmCompletionTokens: type: number format: double description: This is the LLM completion tokens used for the call. llmCachedPromptTokens: type: number format: double description: This is the LLM cached prompt tokens used for the call. ttsCharacters: type: number format: double description: This is the TTS characters used for the call. analysisCostBreakdown: $ref: '#/components/schemas/AnalysisCostBreakdown' description: This is the cost of the analysis. title: CostBreakdown ArtifactPlanRecordingFormat: type: string enum: - wav;l16 - mp3 description: |- This determines the format of the recording. Defaults to `wav;l16`. @default 'wav;l16' title: ArtifactPlanRecordingFormat TranscriptPlan: type: object properties: enabled: type: boolean description: >- This determines whether the transcript is stored in `call.artifact.transcript`. Defaults to true. @default true assistantName: type: string description: >- This is the name of the assistant in the transcript. Defaults to 'AI'. Usage: - If you want to change the name of the assistant in the transcript, set this. Example, here is what the transcript would look like with `assistantName` set to 'Buyer': ``` User: Hello, how are you? Buyer: I'm fine. User: Do you want to buy a car? Buyer: No. ``` @default 'AI' userName: type: string description: >- This is the name of the user in the transcript. Defaults to 'User'. Usage: - If you want to change the name of the user in the transcript, set this. Example, here is what the transcript would look like with `userName` set to 'Seller': ``` Seller: Hello, how are you? AI: I'm fine. Seller: Do you want to buy a car? AI: No. ``` @default 'User' title: TranscriptPlan CreateStructuredOutputDtoType: type: string enum: - ai - regex default: ai description: >- This is the type of structured output. - 'ai': Uses an LLM to extract structured data from the conversation (default). - 'regex': Uses a regex pattern to extract data from the transcript without an LLM. Defaults to 'ai' if not specified. title: CreateStructuredOutputDtoType WorkflowOpenAiModelProvider: type: string enum: - openai description: This is the provider of the model (`openai`). title: WorkflowOpenAiModelProvider WorkflowOpenAiModelModel: type: string enum: - gpt-5.4 - gpt-5.4-mini - gpt-5.4-nano - gpt-5.2 - gpt-5.2-chat-latest - gpt-5.1 - gpt-5.1-chat-latest - gpt-5 - gpt-5-chat-latest - gpt-5-mini - gpt-5-nano - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - chatgpt-4o-latest - o3 - o3-mini - o4-mini - o1-mini - o1-mini-2024-09-12 - gpt-4o-mini-2024-07-18 - gpt-4o-mini - gpt-4o - gpt-4o-2024-05-13 - gpt-4o-2024-08-06 - gpt-4o-2024-11-20 - gpt-4-turbo - gpt-4-turbo-2024-04-09 - gpt-4-turbo-preview - gpt-4-0125-preview - gpt-4-1106-preview - gpt-4 - gpt-4-0613 - gpt-3.5-turbo - gpt-3.5-turbo-0125 - gpt-3.5-turbo-1106 - gpt-3.5-turbo-16k - gpt-3.5-turbo-0613 - gpt-4.1-2025-04-14:westus - gpt-4.1-2025-04-14:eastus2 - gpt-4.1-2025-04-14:eastus - gpt-4.1-2025-04-14:westus3 - gpt-4.1-2025-04-14:northcentralus - gpt-4.1-2025-04-14:southcentralus - gpt-4.1-2025-04-14:westeurope - gpt-4.1-2025-04-14:germanywestcentral - gpt-4.1-2025-04-14:polandcentral - gpt-4.1-2025-04-14:spaincentral - gpt-4.1-mini-2025-04-14:westus - gpt-4.1-mini-2025-04-14:eastus2 - gpt-4.1-mini-2025-04-14:eastus - gpt-4.1-mini-2025-04-14:westus3 - gpt-4.1-mini-2025-04-14:northcentralus - gpt-4.1-mini-2025-04-14:southcentralus - gpt-4.1-mini-2025-04-14:westeurope - gpt-4.1-mini-2025-04-14:germanywestcentral - gpt-4.1-mini-2025-04-14:polandcentral - gpt-4.1-mini-2025-04-14:spaincentral - gpt-4.1-nano-2025-04-14:westus - gpt-4.1-nano-2025-04-14:eastus2 - gpt-4.1-nano-2025-04-14:westus3 - gpt-4.1-nano-2025-04-14:northcentralus - gpt-4.1-nano-2025-04-14:southcentralus - gpt-4o-2024-11-20:swedencentral - gpt-4o-2024-11-20:westus - gpt-4o-2024-11-20:eastus2 - gpt-4o-2024-11-20:eastus - gpt-4o-2024-11-20:westus3 - gpt-4o-2024-11-20:southcentralus - gpt-4o-2024-11-20:westeurope - gpt-4o-2024-11-20:germanywestcentral - gpt-4o-2024-11-20:polandcentral - gpt-4o-2024-11-20:spaincentral - gpt-4o-2024-08-06:westus - gpt-4o-2024-08-06:westus3 - gpt-4o-2024-08-06:eastus - gpt-4o-2024-08-06:eastus2 - gpt-4o-2024-08-06:northcentralus - gpt-4o-2024-08-06:southcentralus - gpt-4o-mini-2024-07-18:westus - gpt-4o-mini-2024-07-18:westus3 - gpt-4o-mini-2024-07-18:eastus - gpt-4o-mini-2024-07-18:eastus2 - gpt-4o-mini-2024-07-18:northcentralus - gpt-4o-mini-2024-07-18:southcentralus - gpt-4o-2024-05-13:eastus2 - gpt-4o-2024-05-13:eastus - gpt-4o-2024-05-13:northcentralus - gpt-4o-2024-05-13:southcentralus - gpt-4o-2024-05-13:westus3 - gpt-4o-2024-05-13:westus - gpt-4-turbo-2024-04-09:eastus2 - gpt-4-0125-preview:eastus - gpt-4-0125-preview:northcentralus - gpt-4-0125-preview:southcentralus - gpt-4-1106-preview:australiaeast - gpt-4-1106-preview:canadaeast - gpt-4-1106-preview:france - gpt-4-1106-preview:india - gpt-4-1106-preview:norway - gpt-4-1106-preview:swedencentral - gpt-4-1106-preview:uk - gpt-4-1106-preview:westus - gpt-4-1106-preview:westus3 - gpt-4-0613:canadaeast - gpt-3.5-turbo-0125:canadaeast - gpt-3.5-turbo-0125:northcentralus - gpt-3.5-turbo-0125:southcentralus - gpt-3.5-turbo-1106:canadaeast - gpt-3.5-turbo-1106:westus description: >- This is the OpenAI model that will be used. When using Vapi OpenAI or your own Azure Credentials, you have the option to specify the region for the selected model. This shouldn't be specified unless you have a specific reason to do so. Vapi will automatically find the fastest region that make sense. This is helpful when you are required to comply with Data Residency rules. Learn more about Azure regions here https://azure.microsoft.com/en-us/explore/global-infrastructure/data-residency/. title: WorkflowOpenAiModelModel WorkflowOpenAIModel: type: object properties: provider: $ref: '#/components/schemas/WorkflowOpenAiModelProvider' description: This is the provider of the model (`openai`). model: $ref: '#/components/schemas/WorkflowOpenAiModelModel' description: >- This is the OpenAI model that will be used. When using Vapi OpenAI or your own Azure Credentials, you have the option to specify the region for the selected model. This shouldn't be specified unless you have a specific reason to do so. Vapi will automatically find the fastest region that make sense. This is helpful when you are required to comply with Data Residency rules. Learn more about Azure regions here https://azure.microsoft.com/en-us/explore/global-infrastructure/data-residency/. temperature: type: number format: double description: This is the temperature of the model. maxTokens: type: number format: double description: This is the max tokens of the model. required: - provider - model title: WorkflowOpenAIModel WorkflowAnthropicModelProvider: type: string enum: - anthropic description: This is the provider of the model (`anthropic`). title: WorkflowAnthropicModelProvider WorkflowAnthropicModelModel: type: string enum: - claude-3-opus-20240229 - claude-3-sonnet-20240229 - claude-3-haiku-20240307 - claude-3-5-sonnet-20240620 - claude-3-5-sonnet-20241022 - claude-3-5-haiku-20241022 - claude-3-7-sonnet-20250219 - claude-opus-4-20250514 - claude-opus-4-5-20251101 - claude-opus-4-6 - claude-sonnet-4-20250514 - claude-sonnet-4-5-20250929 - claude-sonnet-4-6 - claude-haiku-4-5-20251001 description: This is the specific model that will be used. title: WorkflowAnthropicModelModel AnthropicThinkingConfigType: type: string enum: - enabled title: AnthropicThinkingConfigType AnthropicThinkingConfig: type: object properties: type: $ref: '#/components/schemas/AnthropicThinkingConfigType' budgetTokens: type: number format: double description: |- The maximum number of tokens to allocate for thinking. Must be between 1024 and 100000 tokens. required: - type - budgetTokens title: AnthropicThinkingConfig WorkflowAnthropicModel: type: object properties: provider: $ref: '#/components/schemas/WorkflowAnthropicModelProvider' description: This is the provider of the model (`anthropic`). model: $ref: '#/components/schemas/WorkflowAnthropicModelModel' description: This is the specific model that will be used. thinking: $ref: '#/components/schemas/AnthropicThinkingConfig' description: >- This is the optional configuration for Anthropic's thinking feature. - If provided, `maxTokens` must be greater than `thinking.budgetTokens`. temperature: type: number format: double description: This is the temperature of the model. maxTokens: type: number format: double description: This is the max tokens of the model. required: - provider - model title: WorkflowAnthropicModel WorkflowAnthropicBedrockModelProvider: type: string enum: - anthropic-bedrock description: This is the provider of the model (`anthropic-bedrock`). title: WorkflowAnthropicBedrockModelProvider WorkflowAnthropicBedrockModelModel: type: string enum: - claude-3-opus-20240229 - claude-3-sonnet-20240229 - claude-3-haiku-20240307 - claude-3-5-sonnet-20240620 - claude-3-5-sonnet-20241022 - claude-3-5-haiku-20241022 - claude-3-7-sonnet-20250219 - claude-opus-4-20250514 - claude-opus-4-5-20251101 - claude-opus-4-6 - claude-sonnet-4-20250514 - claude-sonnet-4-5-20250929 - claude-sonnet-4-6 - claude-haiku-4-5-20251001 description: This is the specific model that will be used. title: WorkflowAnthropicBedrockModelModel WorkflowAnthropicBedrockModel: type: object properties: provider: $ref: '#/components/schemas/WorkflowAnthropicBedrockModelProvider' description: This is the provider of the model (`anthropic-bedrock`). model: $ref: '#/components/schemas/WorkflowAnthropicBedrockModelModel' description: This is the specific model that will be used. thinking: $ref: '#/components/schemas/AnthropicThinkingConfig' description: >- This is the optional configuration for Anthropic's thinking feature. - If provided, `maxTokens` must be greater than `thinking.budgetTokens`. temperature: type: number format: double description: This is the temperature of the model. maxTokens: type: number format: double description: This is the max tokens of the model. required: - provider - model title: WorkflowAnthropicBedrockModel WorkflowGoogleModelProvider: type: string enum: - google description: This is the provider of the model (`google`). title: WorkflowGoogleModelProvider WorkflowGoogleModelModel: type: string enum: - gemini-3-flash-preview - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.0-flash-thinking-exp - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.0-flash-exp - gemini-2.0-flash-realtime-exp - gemini-1.5-flash - gemini-1.5-flash-002 - gemini-1.5-pro - gemini-1.5-pro-002 - gemini-1.0-pro description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b title: WorkflowGoogleModelModel WorkflowGoogleModel: type: object properties: provider: $ref: '#/components/schemas/WorkflowGoogleModelProvider' description: This is the provider of the model (`google`). model: $ref: '#/components/schemas/WorkflowGoogleModelModel' description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number format: double description: This is the temperature of the model. maxTokens: type: number format: double description: This is the max tokens of the model. required: - provider - model title: WorkflowGoogleModel WorkflowCustomModelProvider: type: string enum: - custom-llm description: This is the provider of the model (`custom-llm`). title: WorkflowCustomModelProvider WorkflowCustomModelMetadataSendMode: type: string enum: - 'off' - variable - destructured description: >- This determines whether metadata is sent in requests to the custom provider. - `off` will not send any metadata. payload will look like `{ messages }` - `variable` will send `assistant.metadata` as a variable on the payload. payload will look like `{ messages, metadata }` - `destructured` will send `assistant.metadata` fields directly on the payload. payload will look like `{ messages, ...metadata }` Further, `variable` and `destructured` will send `call`, `phoneNumber`, and `customer` objects in the payload. Default is `variable`. title: WorkflowCustomModelMetadataSendMode WorkflowCustomModelHeaders: type: object properties: {} description: These are the headers we'll use for the OpenAI client's `headers`. title: WorkflowCustomModelHeaders WorkflowCustomModel: type: object properties: provider: $ref: '#/components/schemas/WorkflowCustomModelProvider' description: This is the provider of the model (`custom-llm`). metadataSendMode: $ref: '#/components/schemas/WorkflowCustomModelMetadataSendMode' description: >- This determines whether metadata is sent in requests to the custom provider. - `off` will not send any metadata. payload will look like `{ messages }` - `variable` will send `assistant.metadata` as a variable on the payload. payload will look like `{ messages, metadata }` - `destructured` will send `assistant.metadata` fields directly on the payload. payload will look like `{ messages, ...metadata }` Further, `variable` and `destructured` will send `call`, `phoneNumber`, and `customer` objects in the payload. Default is `variable`. url: type: string description: >- These is the URL we'll use for the OpenAI client's `baseURL`. Ex. https://openrouter.ai/api/v1 headers: $ref: '#/components/schemas/WorkflowCustomModelHeaders' description: These are the headers we'll use for the OpenAI client's `headers`. timeoutSeconds: type: number format: double description: >- This sets the timeout for the connection to the custom provider without needing to stream any tokens back. Default is 20 seconds. model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number format: double description: This is the temperature of the model. maxTokens: type: number format: double description: This is the max tokens of the model. required: - provider - url - model title: WorkflowCustomModel CreateStructuredOutputDtoModel: oneOf: - $ref: '#/components/schemas/WorkflowOpenAIModel' - $ref: '#/components/schemas/WorkflowAnthropicModel' - $ref: '#/components/schemas/WorkflowAnthropicBedrockModel' - $ref: '#/components/schemas/WorkflowGoogleModel' - $ref: '#/components/schemas/WorkflowCustomModel' description: >- This is the model that will be used to extract the structured output. To provide your own custom system and user prompts for structured output extraction, populate the messages array with your system and user messages. You can specify liquid templating in your system and user messages. Between the system or user messages, you must reference either 'transcript' or 'messages' with the `{{}}` syntax to access the conversation history. Between the system or user messages, you must reference a variation of the structured output with the `{{}}` syntax to access the structured output definition. i.e.: `{{structuredOutput}}` `{{structuredOutput.name}}` `{{structuredOutput.description}}` `{{structuredOutput.schema}}` If model is not specified, GPT-4.1 will be used by default for extraction, utilizing default system and user prompts. If messages or required fields are not specified, the default system and user prompts will be used. title: CreateStructuredOutputDtoModel ComplianceOverride: type: object properties: forceStoreOnHipaaEnabled: type: boolean description: >- Force storage for this output under HIPAA. Only enable if output contains no sensitive data. title: ComplianceOverride JsonSchemaType: type: string enum: - string - number - integer - boolean - array - object description: >- This is the type of output you'd like. `string`, `number`, `integer`, `boolean` are the primitive types and should be obvious. `array` and `object` are more interesting and quite powerful. They allow you to define nested structures. For `array`, you can define the schema of the items in the array using the `items` property. For `object`, you can define the properties of the object using the `properties` property. title: JsonSchemaType JsonSchemaFormat: type: string enum: - date-time - time - date - duration - email - hostname - ipv4 - ipv6 - uuid description: >- This is the format of the string. To pass a regex, use the `pattern` property instead. OpenAI documentation: https://platform.openai.com/docs/guides/structured-outputs?api-mode=chat&type-restrictions=string-restrictions title: JsonSchemaFormat JsonSchema: type: object properties: type: $ref: '#/components/schemas/JsonSchemaType' description: >- This is the type of output you'd like. `string`, `number`, `integer`, `boolean` are the primitive types and should be obvious. `array` and `object` are more interesting and quite powerful. They allow you to define nested structures. For `array`, you can define the schema of the items in the array using the `items` property. For `object`, you can define the properties of the object using the `properties` property. items: $ref: '#/components/schemas/JsonSchema' description: >- This is required if the type is "array". This is the schema of the items in the array. This is a recursive reference to JsonSchema. properties: type: object additionalProperties: $ref: '#/components/schemas/JsonSchema' description: >- This is required if the type is "object". This specifies the properties of the object. This is a map of property names to JsonSchema objects. description: type: string description: >- This is the description to help the model understand what it needs to output. pattern: type: string description: >- This is the pattern of the string. This is a regex that will be used to validate the data in question. To use a common format, use the `format` property instead. OpenAI documentation: https://platform.openai.com/docs/guides/structured-outputs#supported-properties format: $ref: '#/components/schemas/JsonSchemaFormat' description: >- This is the format of the string. To pass a regex, use the `pattern` property instead. OpenAI documentation: https://platform.openai.com/docs/guides/structured-outputs?api-mode=chat&type-restrictions=string-restrictions required: type: array items: type: string description: |- This is a list of properties that are required. This only makes sense if the type is "object". enum: type: array items: type: string description: >- This array specifies the allowed values that can be used to restrict the output of the model. title: type: string description: This is the title of the schema. required: - type title: JsonSchema CreateStructuredOutputDTO: type: object properties: type: $ref: '#/components/schemas/CreateStructuredOutputDtoType' description: >- This is the type of structured output. - 'ai': Uses an LLM to extract structured data from the conversation (default). - 'regex': Uses a regex pattern to extract data from the transcript without an LLM. Defaults to 'ai' if not specified. regex: type: string description: >- This is the regex pattern to match against the transcript. Only used when type is 'regex'. Supports both raw patterns (e.g. '\d+') and regex literal format (e.g. '/\d+/gi'). Uses RE2 syntax for safety. The result depends on the schema type: - boolean: true if the pattern matches, false otherwise - string: the first match or first capture group - number/integer: the first match parsed as a number - array: all matches model: $ref: '#/components/schemas/CreateStructuredOutputDtoModel' description: >- This is the model that will be used to extract the structured output. To provide your own custom system and user prompts for structured output extraction, populate the messages array with your system and user messages. You can specify liquid templating in your system and user messages. Between the system or user messages, you must reference either 'transcript' or 'messages' with the `{{}}` syntax to access the conversation history. Between the system or user messages, you must reference a variation of the structured output with the `{{}}` syntax to access the structured output definition. i.e.: `{{structuredOutput}}` `{{structuredOutput.name}}` `{{structuredOutput.description}}` `{{structuredOutput.schema}}` If model is not specified, GPT-4.1 will be used by default for extraction, utilizing default system and user prompts. If messages or required fields are not specified, the default system and user prompts will be used. compliancePlan: $ref: '#/components/schemas/ComplianceOverride' description: >- Compliance configuration for this output. Only enable overrides if no sensitive data will be stored. name: type: string description: This is the name of the structured output. schema: $ref: '#/components/schemas/JsonSchema' description: >- This is the JSON Schema definition for the structured output. This is required when creating a structured output. Defines the structure and validation rules for the data that will be extracted. Supports all JSON Schema features including: - Objects and nested properties - Arrays and array validation - String, number, boolean, and null types - Enums and const values - Validation constraints (min/max, patterns, etc.) - Composition with allOf, anyOf, oneOf description: type: string description: >- This is the description of what the structured output extracts. Use this to provide context about what data will be extracted and how it will be used. assistantIds: type: array items: type: string description: >- These are the assistant IDs that this structured output is linked to. When linked to assistants, this structured output will be available for extraction during those assistant's calls. workflowIds: type: array items: type: string description: >- These are the workflow IDs that this structured output is linked to. When linked to workflows, this structured output will be available for extraction during those workflow's execution. required: - name - schema title: CreateStructuredOutputDTO ScorecardMetricConditionsItems: type: object properties: {} title: ScorecardMetricConditionsItems ScorecardMetric: type: object properties: structuredOutputId: type: string description: >- This is the unique identifier for the structured output that will be used to evaluate the scorecard. The structured output must be of type number or boolean only for now. conditions: type: array items: $ref: '#/components/schemas/ScorecardMetricConditionsItems' description: >- These are the conditions that will be used to evaluate the scorecard. Each condition will have a comparator, value, and points that will be used to calculate the final score. The points will be added to the overall score if the condition is met. The overall score will be normalized to a 100 point scale to ensure uniformity across different scorecards. required: - structuredOutputId - conditions title: ScorecardMetric CreateScorecardDTO: type: object properties: name: type: string description: >- This is the name of the scorecard. It is only for user reference and will not be used for any evaluation. description: type: string description: >- This is the description of the scorecard. It is only for user reference and will not be used for any evaluation. metrics: type: array items: $ref: '#/components/schemas/ScorecardMetric' description: >- These are the metrics that will be used to evaluate the scorecard. Each metric will have a set of conditions and points that will be used to generate the score. assistantIds: type: array items: type: string description: >- These are the assistant IDs that this scorecard is linked to. When linked to assistants, this scorecard will be available for evaluation during those assistants' calls. required: - metrics title: CreateScorecardDTO ArtifactPlan: type: object properties: recordingEnabled: type: boolean description: >- This determines whether assistant's calls are recorded. Defaults to true. Usage: - If you don't want to record the calls, set this to false. - If you want to record the calls when `assistant.hipaaEnabled` (deprecated) or `assistant.compliancePlan.hipaaEnabled` explicity set this to true and make sure to provide S3 or GCP credentials on the Provider Credentials page in the Dashboard. You can find the recording at `call.artifact.recordingUrl` and `call.artifact.stereoRecordingUrl` after the call is ended. @default true recordingFormat: $ref: '#/components/schemas/ArtifactPlanRecordingFormat' description: |- This determines the format of the recording. Defaults to `wav;l16`. @default 'wav;l16' recordingUseCustomStorageEnabled: type: boolean description: >- This determines whether to use custom storage (S3 or GCP) for call recordings when storage credentials are configured. When set to false, recordings will be stored on Vapi's storage instead of your custom storage, even if you have custom storage credentials configured. Usage: - Set to false if you have custom storage configured but want to store recordings on Vapi's storage for this assistant. - Set to true (or leave unset) to use your custom storage for recordings when available. @default true videoRecordingEnabled: type: boolean description: >- This determines whether the video is recorded during the call. Defaults to false. Only relevant for `webCall` type. You can find the video recording at `call.artifact.videoRecordingUrl` after the call is ended. @default false fullMessageHistoryEnabled: type: boolean description: >- This determines whether the artifact contains the full message history, even after handoff context engineering. Defaults to false. pcapEnabled: type: boolean description: >- This determines whether the SIP packet capture is enabled. Defaults to true. Only relevant for `phone` type calls where phone number's provider is `vapi` or `byo-phone-number`. You can find the packet capture at `call.artifact.pcapUrl` after the call is ended. @default true pcapS3PathPrefix: type: string description: >- This is the path where the SIP packet capture will be uploaded. This is only used if you have provided S3 or GCP credentials on the Provider Credentials page in the Dashboard. If credential.s3PathPrefix or credential.bucketPlan.path is set, this will append to it. Usage: - If you want to upload the packet capture to a specific path, set this to the path. Example: `/my-assistant-captures`. - If you want to upload the packet capture to the root of the bucket, set this to `/`. @default '/' pcapUseCustomStorageEnabled: type: boolean description: >- This determines whether to use custom storage (S3 or GCP) for SIP packet captures when storage credentials are configured. When set to false, packet captures will be stored on Vapi's storage instead of your custom storage, even if you have custom storage credentials configured. Usage: - Set to false if you have custom storage configured but want to store packet captures on Vapi's storage for this assistant. - Set to true (or leave unset) to use your custom storage for packet captures when available. @default true loggingEnabled: type: boolean description: |- This determines whether the call logs are enabled. Defaults to true. @default true loggingUseCustomStorageEnabled: type: boolean description: >- This determines whether to use custom storage (S3 or GCP) for call logs when storage credentials are configured. When set to false, logs will be stored on Vapi's storage instead of your custom storage, even if you have custom storage credentials configured. Usage: - Set to false if you have custom storage configured but want to store logs on Vapi's storage for this assistant. - Set to true (or leave unset) to use your custom storage for logs when available. @default true transcriptPlan: $ref: '#/components/schemas/TranscriptPlan' description: >- This is the plan for `call.artifact.transcript`. To disable, set `transcriptPlan.enabled` to false. recordingPath: type: string description: >- This is the path where the recording will be uploaded. This is only used if you have provided S3 or GCP credentials on the Provider Credentials page in the Dashboard. If credential.s3PathPrefix or credential.bucketPlan.path is set, this will append to it. Usage: - If you want to upload the recording to a specific path, set this to the path. Example: `/my-assistant-recordings`. - If you want to upload the recording to the root of the bucket, set this to `/`. @default '/' structuredOutputIds: type: array items: type: string description: >- This is an array of structured output IDs to be calculated during the call. The outputs will be extracted and stored in `call.artifact.structuredOutputs` after the call is ended. structuredOutputs: type: array items: $ref: '#/components/schemas/CreateStructuredOutputDTO' description: >- This is an array of transient structured outputs to be calculated during the call. The outputs will be extracted and stored in `call.artifact.structuredOutputs` after the call is ended. Use this to provide inline structured output configurations instead of referencing existing ones via structuredOutputIds. scorecardIds: type: array items: type: string description: >- This is an array of scorecard IDs that will be evaluated based on the structured outputs extracted during the call. The scorecards will be evaluated and the results will be stored in `call.artifact.scorecards` after the call has ended. scorecards: type: array items: $ref: '#/components/schemas/CreateScorecardDTO' description: >- This is the array of scorecards that will be evaluated based on the structured outputs extracted during the call. The scorecards will be evaluated and the results will be stored in `call.artifact.scorecards` after the call has ended. loggingPath: type: string description: >- This is the path where the call logs will be uploaded. This is only used if you have provided S3 or GCP credentials on the Provider Credentials page in the Dashboard. If credential.s3PathPrefix or credential.bucketPlan.path is set, this will append to it. Usage: - If you want to upload the call logs to a specific path, set this to the path. Example: `/my-assistant-logs`. - If you want to upload the call logs to the root of the bucket, set this to `/`. @default '/' title: ArtifactPlan AnalysisStructuredData: type: object properties: {} description: >- This is the structured data extracted from the call. Customize by setting `assistant.analysisPlan.structuredDataPrompt` and/or `assistant.analysisPlan.structuredDataSchema`. title: AnalysisStructuredData AnalysisStructuredDataMultiItems: type: object properties: {} title: AnalysisStructuredDataMultiItems Analysis: type: object properties: summary: type: string description: >- This is the summary of the call. Customize by setting `assistant.analysisPlan.summaryPrompt`. structuredData: $ref: '#/components/schemas/AnalysisStructuredData' description: >- This is the structured data extracted from the call. Customize by setting `assistant.analysisPlan.structuredDataPrompt` and/or `assistant.analysisPlan.structuredDataSchema`. structuredDataMulti: type: array items: $ref: '#/components/schemas/AnalysisStructuredDataMultiItems' description: >- This is the structured data catalog of the call. Customize by setting `assistant.analysisPlan.structuredDataMultiPlan`. successEvaluation: type: string description: >- This is the evaluation of the call. Customize by setting `assistant.analysisPlan.successEvaluationPrompt` and/or `assistant.analysisPlan.successEvaluationRubric`. title: Analysis MonitorResult: type: object properties: monitorId: type: string filterPassed: type: boolean required: - monitorId - filterPassed title: MonitorResult Monitor: type: object properties: monitors: type: array items: $ref: '#/components/schemas/MonitorResult' listenUrl: type: string description: >- This is the URL where the assistant's calls can be listened to in real-time. To enable, set `assistant.monitorPlan.listenEnabled` to `true`. controlUrl: type: string description: >- This is the URL where the assistant's calls can be controlled in real-time. To enable, set `assistant.monitorPlan.controlEnabled` to `true`. title: Monitor ArtifactMessagesItems: oneOf: - $ref: '#/components/schemas/UserMessage' - $ref: '#/components/schemas/SystemMessage' - $ref: '#/components/schemas/BotMessage' - $ref: '#/components/schemas/ToolCallMessage' - $ref: '#/components/schemas/ToolCallResultMessage' title: ArtifactMessagesItems OpenAiMessageRole: type: string enum: - assistant - function - user - system - tool title: OpenAiMessageRole OpenAIMessage: type: object properties: content: type: - string - 'null' role: $ref: '#/components/schemas/OpenAiMessageRole' required: - content - role title: OpenAIMessage Mono: type: object properties: combinedUrl: type: string description: >- This is the combined recording url for the call. To enable, set `assistant.artifactPlan.recordingEnabled`. assistantUrl: type: string description: >- This is the mono recording url for the assistant. To enable, set `assistant.artifactPlan.recordingEnabled`. customerUrl: type: string description: >- This is the mono recording url for the customer. To enable, set `assistant.artifactPlan.recordingEnabled`. title: Mono Recording: type: object properties: stereoUrl: type: string description: >- This is the stereo recording url for the call. To enable, set `assistant.artifactPlan.recordingEnabled`. videoUrl: type: string description: >- This is the video recording url for the call. To enable, set `assistant.artifactPlan.videoRecordingEnabled`. videoRecordingStartDelaySeconds: type: number format: double description: >- This is video recording start delay in ms. To enable, set `assistant.artifactPlan.videoRecordingEnabled`. This can be used to align the playback of the recording with artifact.messages timestamps. mono: $ref: '#/components/schemas/Mono' description: >- This is the mono recording url for the call. To enable, set `assistant.artifactPlan.recordingEnabled`. title: Recording NodeArtifactMessagesItems: oneOf: - $ref: '#/components/schemas/UserMessage' - $ref: '#/components/schemas/SystemMessage' - $ref: '#/components/schemas/BotMessage' - $ref: '#/components/schemas/ToolCallMessage' - $ref: '#/components/schemas/ToolCallResultMessage' title: NodeArtifactMessagesItems NodeArtifactVariableValues: type: object properties: {} description: These are the variable values that were extracted from the node. title: NodeArtifactVariableValues NodeArtifact: type: object properties: messages: type: array items: $ref: '#/components/schemas/NodeArtifactMessagesItems' description: These are the messages that were spoken during the node. nodeName: type: string description: This is the node name. variableValues: $ref: '#/components/schemas/NodeArtifactVariableValues' description: These are the variable values that were extracted from the node. title: NodeArtifact AssistantActivation: type: object properties: assistantName: type: string description: This is the name of the assistant that was active during the call. assistantId: type: string description: This is the ID of the assistant that was active during the call. required: - assistantName title: AssistantActivation ArtifactVariableValues: type: object properties: {} description: These are the variable values at the end of the workflow execution. title: ArtifactVariableValues TurnLatency: type: object properties: modelLatency: type: number format: double description: This is the model latency for the first token. voiceLatency: type: number format: double description: This is the voice latency from the model output. transcriberLatency: type: number format: double description: This is the transcriber latency from the user speech. endpointingLatency: type: number format: double description: This is the endpointing latency. turnLatency: type: number format: double description: This is the latency for the whole turn. title: TurnLatency PerformanceMetrics: type: object properties: turnLatencies: type: array items: $ref: '#/components/schemas/TurnLatency' description: These are the individual latencies for each turn. modelLatencyAverage: type: number format: double description: This is the average latency for the model to output the first token. voiceLatencyAverage: type: number format: double description: This is the average latency for the text to speech. transcriberLatencyAverage: type: number format: double description: This is the average latency for the transcriber. endpointingLatencyAverage: type: number format: double description: This is the average latency for the endpointing. turnLatencyAverage: type: number format: double description: This is the average latency for complete turns. fromTransportLatencyAverage: type: number format: double description: >- This is the average latency for packets received from the transport provider in milliseconds. toTransportLatencyAverage: type: number format: double description: >- This is the average latency for packets sent to the transport provider in milliseconds. numUserInterrupted: type: number format: double description: >- This is the number of times the user was interrupted by the assistant during the call. numAssistantInterrupted: type: number format: double description: >- This is the number of times the assistant was interrupted by the user during the call. title: PerformanceMetrics ArtifactStructuredOutputs: type: object properties: {} description: >- These are the structured outputs that will be extracted from the call. To enable, set `assistant.artifactPlan.structuredOutputIds` with the IDs of the structured outputs you want to extract. title: ArtifactStructuredOutputs ArtifactScorecards: type: object properties: {} description: >- These are the scorecards that have been evaluated based on the structured outputs extracted during the call. To enable, set `assistant.artifactPlan.scorecardIds` or `assistant.artifactPlan.scorecards` with the IDs or objects of the scorecards you want to evaluate. title: ArtifactScorecards Artifact: type: object properties: messages: type: array items: $ref: '#/components/schemas/ArtifactMessagesItems' description: These are the messages that were spoken during the call. messagesOpenAIFormatted: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: >- These are the messages that were spoken during the call, formatted for OpenAI. recordingUrl: type: string description: >- This is the recording url for the call. To enable, set `assistant.artifactPlan.recordingEnabled`. stereoRecordingUrl: type: string description: >- This is the stereo recording url for the call. To enable, set `assistant.artifactPlan.recordingEnabled`. videoRecordingUrl: type: string description: >- This is video recording url for the call. To enable, set `assistant.artifactPlan.videoRecordingEnabled`. videoRecordingStartDelaySeconds: type: number format: double description: >- This is video recording start delay in ms. To enable, set `assistant.artifactPlan.videoRecordingEnabled`. This can be used to align the playback of the recording with artifact.messages timestamps. recording: $ref: '#/components/schemas/Recording' description: >- This is the recording url for the call. To enable, set `assistant.artifactPlan.recordingEnabled`. transcript: type: string description: >- This is the transcript of the call. This is derived from `artifact.messages` but provided for convenience. pcapUrl: type: string description: >- This is the packet capture url for the call. This is only available for `phone` type calls where phone number's provider is `vapi` or `byo-phone-number`. logUrl: type: string description: >- This is the url for the call logs. This includes all logging output during the call for debugging purposes. nodes: type: array items: $ref: '#/components/schemas/NodeArtifact' description: >- This is the history of workflow nodes that were executed during the call. assistantActivations: type: array items: $ref: '#/components/schemas/AssistantActivation' description: >- Ordered list of assistants that were active during the call, including after transfers and handoffs. variableValues: $ref: '#/components/schemas/ArtifactVariableValues' description: These are the variable values at the end of the workflow execution. performanceMetrics: $ref: '#/components/schemas/PerformanceMetrics' description: >- This is the performance metrics for the call. It contains the turn latency, broken down by component. structuredOutputs: $ref: '#/components/schemas/ArtifactStructuredOutputs' description: >- These are the structured outputs that will be extracted from the call. To enable, set `assistant.artifactPlan.structuredOutputIds` with the IDs of the structured outputs you want to extract. scorecards: $ref: '#/components/schemas/ArtifactScorecards' description: >- These are the scorecards that have been evaluated based on the structured outputs extracted during the call. To enable, set `assistant.artifactPlan.scorecardIds` or `assistant.artifactPlan.scorecards` with the IDs or objects of the scorecards you want to evaluate. transfers: type: array items: type: string description: >- These are the transfer records from warm transfers, including destinations, transcripts, and status. structuredOutputsLastUpdatedAt: type: string format: date-time description: This is when the structured outputs were last updated title: Artifact RecordingConsentType: type: object properties: {} description: This is the type of recording consent. title: RecordingConsentType RecordingConsent: type: object properties: type: $ref: '#/components/schemas/RecordingConsentType' description: This is the type of recording consent. grantedAt: type: string format: date-time description: |- This is the date and time the recording consent was granted. If not specified, it means the recording consent was not granted. required: - type title: RecordingConsent Compliance: type: object properties: recordingConsent: $ref: '#/components/schemas/RecordingConsent' description: >- This is the recording consent of the call. Configure in `assistant.compliancePlan.recordingConsentPlan`. title: Compliance AssemblyAiTranscriberProvider: type: string enum: - assembly-ai description: This is the transcription provider that will be used. title: AssemblyAiTranscriberProvider AssemblyAiTranscriberLanguage: type: string enum: - multi - en description: This is the language that will be set for the transcription. title: AssemblyAiTranscriberLanguage AssemblyAiTranscriberSpeechModel: type: string enum: - universal-streaming-english - universal-streaming-multilingual description: |- This is the speech model used for the streaming session. Note: Keyterms prompting is not supported with multilingual streaming. @default 'universal-streaming-english' title: AssemblyAiTranscriberSpeechModel FallbackAssemblyAiTranscriberProvider: type: string enum: - assembly-ai description: This is the transcription provider that will be used. title: FallbackAssemblyAiTranscriberProvider FallbackAssemblyAiTranscriberLanguage: type: string enum: - multi - en description: This is the language that will be set for the transcription. title: FallbackAssemblyAiTranscriberLanguage FallbackAssemblyAiTranscriberSpeechModel: type: string enum: - universal-streaming-english - universal-streaming-multilingual description: |- This is the speech model used for the streaming session. Note: Keyterms prompting is not supported with multilingual streaming. @default 'universal-streaming-english' title: FallbackAssemblyAiTranscriberSpeechModel FallbackAssemblyAITranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackAssemblyAiTranscriberProvider' description: This is the transcription provider that will be used. language: $ref: '#/components/schemas/FallbackAssemblyAiTranscriberLanguage' description: This is the language that will be set for the transcription. confidenceThreshold: type: number format: double description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 formatTurns: type: boolean description: |- This enables formatting of transcripts. @default true endOfTurnConfidenceThreshold: type: number format: double description: >- This is the end of turn confidence threshold. The minimum confidence that the end of turn is detected. Note: Only used if startSpeakingPlan.smartEndpointingPlan is not set. @min 0 @max 1 @default 0.7 minEndOfTurnSilenceWhenConfident: type: number format: double description: >- This is the minimum end of turn silence when confident in milliseconds. Note: Only used if startSpeakingPlan.smartEndpointingPlan is not set. @default 160 wordFinalizationMaxWaitTime: type: number format: double maxTurnSilence: type: number format: double description: >- This is the maximum turn silence time in milliseconds. Note: Only used if startSpeakingPlan.smartEndpointingPlan is not set. @default 400 vadAssistedEndpointingEnabled: type: boolean description: >- Use VAD to assist with endpointing decisions from the transcriber. When enabled, transcriber endpointing will be buffered if VAD detects the user is still speaking, preventing premature turn-taking. When disabled, transcriber endpointing will be used immediately regardless of VAD state, allowing for quicker but more aggressive turn-taking. Note: Only used if startSpeakingPlan.smartEndpointingPlan is not set. @default true speechModel: $ref: '#/components/schemas/FallbackAssemblyAiTranscriberSpeechModel' description: >- This is the speech model used for the streaming session. Note: Keyterms prompting is not supported with multilingual streaming. @default 'universal-streaming-english' realtimeUrl: type: string description: The WebSocket URL that the transcriber connects to. wordBoost: type: array items: type: string description: Add up to 2500 characters of custom vocabulary. keytermsPrompt: type: array items: type: string description: >- Keyterms prompting improves recognition accuracy for specific words and phrases. Can include up to 100 keyterms, each up to 50 characters. Costs an additional $0.04/hour when enabled. endUtteranceSilenceThreshold: type: number format: double description: The duration of the end utterance silence threshold in milliseconds. disablePartialTranscripts: type: boolean description: >- Disable partial transcripts. Set to `true` to not receive partial transcripts. Defaults to `false`. required: - provider title: FallbackAssemblyAITranscriber FallbackAzureSpeechTranscriberProvider: type: string enum: - azure description: This is the transcription provider that will be used. title: FallbackAzureSpeechTranscriberProvider FallbackAzureSpeechTranscriberLanguage: type: string enum: - af-ZA - am-ET - ar-AE - ar-BH - ar-DZ - ar-EG - ar-IL - ar-IQ - ar-JO - ar-KW - ar-LB - ar-LY - ar-MA - ar-OM - ar-PS - ar-QA - ar-SA - ar-SY - ar-TN - ar-YE - az-AZ - bg-BG - bn-IN - bs-BA - ca-ES - cs-CZ - cy-GB - da-DK - de-AT - de-CH - de-DE - el-GR - en-AU - en-CA - en-GB - en-GH - en-HK - en-IE - en-IN - en-KE - en-NG - en-NZ - en-PH - en-SG - en-TZ - en-US - en-ZA - es-AR - es-BO - es-CL - es-CO - es-CR - es-CU - es-DO - es-EC - es-ES - es-GQ - es-GT - es-HN - es-MX - es-NI - es-PA - es-PE - es-PR - es-PY - es-SV - es-US - es-UY - es-VE - et-EE - eu-ES - fa-IR - fi-FI - fil-PH - fr-BE - fr-CA - fr-CH - fr-FR - ga-IE - gl-ES - gu-IN - he-IL - hi-IN - hr-HR - hu-HU - hy-AM - id-ID - is-IS - it-CH - it-IT - ja-JP - jv-ID - ka-GE - kk-KZ - km-KH - kn-IN - ko-KR - lo-LA - lt-LT - lv-LV - mk-MK - ml-IN - mn-MN - mr-IN - ms-MY - mt-MT - my-MM - nb-NO - ne-NP - nl-BE - nl-NL - pa-IN - pl-PL - ps-AF - pt-BR - pt-PT - ro-RO - ru-RU - si-LK - sk-SK - sl-SI - so-SO - sq-AL - sr-RS - sv-SE - sw-KE - sw-TZ - ta-IN - te-IN - th-TH - tr-TR - uk-UA - ur-IN - uz-UZ - vi-VN - wuu-CN - yue-CN - zh-CN - zh-CN-shandong - zh-CN-sichuan - zh-HK - zh-TW - zu-ZA description: >- This is the language that will be set for the transcription. The list of languages Azure supports can be found here: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=stt title: FallbackAzureSpeechTranscriberLanguage FallbackAzureSpeechTranscriberSegmentationStrategy: type: string enum: - Default - Time - Semantic description: >- Controls how phrase boundaries are detected, enabling either simple time/silence heuristics or more advanced semantic segmentation. title: FallbackAzureSpeechTranscriberSegmentationStrategy FallbackAzureSpeechTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackAzureSpeechTranscriberProvider' description: This is the transcription provider that will be used. language: $ref: '#/components/schemas/FallbackAzureSpeechTranscriberLanguage' description: >- This is the language that will be set for the transcription. The list of languages Azure supports can be found here: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=stt segmentationStrategy: $ref: >- #/components/schemas/FallbackAzureSpeechTranscriberSegmentationStrategy description: >- Controls how phrase boundaries are detected, enabling either simple time/silence heuristics or more advanced semantic segmentation. segmentationSilenceTimeoutMs: type: number format: double description: >- Duration of detected silence after which the service finalizes a phrase. Configure to adjust sensitivity to pauses in speech. segmentationMaximumTimeMs: type: number format: double description: >- Maximum duration a segment can reach before being cut off when using time-based segmentation. required: - provider title: FallbackAzureSpeechTranscriber FallbackCustomTranscriberProvider: type: string enum: - custom-transcriber description: >- This is the transcription provider that will be used. Use `custom-transcriber` for providers that are not natively supported. title: FallbackCustomTranscriberProvider ServerHeaders: type: object properties: {} description: >- These are the headers to include in the request. Each key-value pair represents a header name and its value. Note: Specifying an Authorization header here will override the authorization provided by the `credentialId` (if provided). This is an anti-pattern and should be avoided outside of edge case scenarios. title: ServerHeaders BackoffPlanType: type: string enum: - fixed - exponential description: |- This is the type of backoff plan to use. Defaults to fixed. @default fixed title: BackoffPlanType BackoffPlanExcludedStatusCodesItems: type: object properties: {} title: BackoffPlanExcludedStatusCodesItems BackoffPlan: type: object properties: type: $ref: '#/components/schemas/BackoffPlanType' description: |- This is the type of backoff plan to use. Defaults to fixed. @default fixed maxRetries: type: number format: double description: >- This is the maximum number of retries to attempt if the request fails. Defaults to 0 (no retries). @default 0 baseDelaySeconds: type: number format: double description: >- This is the base delay in seconds. For linear backoff, this is the delay between each retry. For exponential backoff, this is the initial delay. excludedStatusCodes: type: array items: $ref: '#/components/schemas/BackoffPlanExcludedStatusCodesItems' description: >- This is the excluded status codes. If the response status code is in this list, the request will not be retried. By default, the request will be retried for any non-2xx status code. required: - type - maxRetries - baseDelaySeconds title: BackoffPlan Server: type: object properties: timeoutSeconds: type: number format: double description: >- This is the timeout in seconds for the request. Defaults to 20 seconds. @default 20 credentialId: type: string description: The credential ID for server authentication staticIpAddressesEnabled: type: boolean description: >- If enabled, requests will originate from a static set of IPs owned and managed by Vapi. @default false encryptedPaths: type: array items: type: string description: >- This is the paths to encrypt in the request body if credentialId and encryptionPlan are defined. url: type: string description: This is where the request will be sent. headers: $ref: '#/components/schemas/ServerHeaders' description: >- These are the headers to include in the request. Each key-value pair represents a header name and its value. Note: Specifying an Authorization header here will override the authorization provided by the `credentialId` (if provided). This is an anti-pattern and should be avoided outside of edge case scenarios. backoffPlan: $ref: '#/components/schemas/BackoffPlan' description: >- This is the backoff plan if the request fails. Defaults to undefined (the request will not be retried). @default undefined (the request will not be retried) title: Server FallbackCustomTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackCustomTranscriberProvider' description: >- This is the transcription provider that will be used. Use `custom-transcriber` for providers that are not natively supported. server: $ref: '#/components/schemas/Server' description: >- This is where the transcription request will be sent. Usage: 1. Vapi will initiate a websocket connection with `server.url`. 2. Vapi will send an initial text frame with the sample rate. Format: ``` { "type": "start", "encoding": "linear16", // 16-bit raw PCM format "container": "raw", "sampleRate": {{sampleRate}}, "channels": 2 // customer is channel 0, assistant is channel 1 } ``` 3. Vapi will send the audio data in 16-bit raw PCM format as binary frames. 4. You can read the messages something like this: ``` ws.on('message', (data, isBinary) => { if (isBinary) { pcmBuffer = Buffer.concat([pcmBuffer, data]); console.log(`Received PCM data, buffer size: ${pcmBuffer.length}`); } else { console.log('Received message:', JSON.parse(data.toString())); } }); ``` 5. You will respond with transcriptions as you have them. Format: ``` { "type": "transcriber-response", "transcription": "Hello, world!", "channel": "customer" | "assistant" } ``` required: - provider - server title: FallbackCustomTranscriber FallbackDeepgramTranscriberProvider: type: string enum: - deepgram description: This is the transcription provider that will be used. title: FallbackDeepgramTranscriberProvider DeepgramTranscriberModel: type: string enum: - flux-general-en - nova-3 - nova-3-general - nova-3-medical - nova-2 - nova-2-general - nova-2-meeting - nova-2-phonecall - nova-2-finance - nova-2-conversationalai - nova-2-voicemail - nova-2-video - nova-2-medical - nova-2-drivethru - nova-2-automotive - nova - nova-general - nova-phonecall - nova-medical - enhanced - enhanced-general - enhanced-meeting - enhanced-phonecall - enhanced-finance - base - base-general - base-meeting - base-phonecall - base-finance - base-conversationalai - base-voicemail - base-video - whisper title: DeepgramTranscriberModel DeepgramTranscriberLanguage: type: string enum: - bg - ca - cs - da - da-DK - de - de-CH - el - en - en-AU - en-GB - en-IN - en-NZ - en-US - es - es-419 - es-LATAM - et - fi - fr - fr-CA - hi - hi-Latn - hu - id - it - ja - ko - ko-KR - lt - lv - ms - multi - nl - nl-BE - 'no' - pl - pt - pt-BR - ro - ru - sk - sv - sv-SE - ta - taq - th - th-TH - tr - uk - vi - zh - zh-CN - zh-Hans - zh-Hant - zh-TW title: DeepgramTranscriberLanguage FallbackDeepgramTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackDeepgramTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/DeepgramTranscriberModel' description: >- This is the Deepgram model that will be used. A list of models can be found here: https://developers.deepgram.com/docs/models-languages-overview language: $ref: '#/components/schemas/DeepgramTranscriberLanguage' description: >- This is the language that will be set for the transcription. The list of languages Deepgram supports can be found here: https://developers.deepgram.com/docs/models-languages-overview smartFormat: type: boolean description: >- This will be use smart format option provided by Deepgram. It's default disabled because it can sometimes format numbers as times but it's getting better. mipOptOut: type: boolean default: false description: >- If set to true, this will add mip_opt_out=true as a query parameter of all API requests. See https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#want-to-opt-out This will only be used if you are using your own Deepgram API key. @default false numerals: type: boolean description: >- If set to true, this will cause deepgram to convert spoken numbers to literal numerals. For example, "my phone number is nine-seven-two..." would become "my phone number is 972..." @default false profanityFilter: type: boolean description: >- If set to true, Deepgram will replace profanity in transcripts with surrounding asterisks, e.g. "f***". @default false confidenceThreshold: type: number format: double description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 eagerEotThreshold: type: number format: double description: >- Eager end-of-turn confidence required to fire a eager end-of-turn event. Setting a value here will enable EagerEndOfTurn and SpeechResumed events. It is disabled by default. Only used with Flux models. eotThreshold: type: number format: double description: >- End-of-turn confidence required to finish a turn. Only used with Flux models. @default 0.7 eotTimeoutMs: type: number format: double description: >- A turn will be finished when this much time has passed after speech, regardless of EOT confidence. Only used with Flux models. @default 5000 keywords: type: array items: type: string description: >- These keywords are passed to the transcription model to help it pick up use-case specific words. Anything that may not be a common word, like your company name, should be added here. keyterm: type: array items: type: string description: >- Keyterm Prompting allows you improve Keyword Recall Rate (KRR) for important keyterms or phrases up to 90%. endpointing: type: number format: double description: >- This is the timeout after which Deepgram will send transcription on user silence. You can read in-depth documentation here: https://developers.deepgram.com/docs/endpointing. Here are the most important bits: - Defaults to 10. This is recommended for most use cases to optimize for latency. - 10 can cause some missing transcriptions since because of the shorter context. This mostly happens for one-word utterances. For those uses cases, it's recommended to try 300. It will add a bit of latency but the quality and reliability of the experience will be better. - If neither 10 nor 300 work, contact support@vapi.ai and we'll find another solution. @default 10 required: - provider title: FallbackDeepgramTranscriber FallbackElevenLabsTranscriberProvider: type: string enum: - 11labs description: This is the transcription provider that will be used. title: FallbackElevenLabsTranscriberProvider FallbackElevenLabsTranscriberModel0: type: string enum: - scribe_v1 - scribe_v2 - scribe_v2_realtime title: FallbackElevenLabsTranscriberModel0 FallbackElevenLabsTranscriberModel: oneOf: - $ref: '#/components/schemas/FallbackElevenLabsTranscriberModel0' description: This is the model that will be used for the transcription. title: FallbackElevenLabsTranscriberModel FallbackElevenLabsTranscriberLanguage: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu description: This is the language that will be used for the transcription. title: FallbackElevenLabsTranscriberLanguage FallbackElevenLabsTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackElevenLabsTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/FallbackElevenLabsTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/FallbackElevenLabsTranscriberLanguage' description: This is the language that will be used for the transcription. silenceThresholdSeconds: type: number format: double description: >- This is the number of seconds of silence before VAD commits (0.3-3.0). confidenceThreshold: type: number format: double description: >- This is the VAD sensitivity (0.1-0.9, lower indicates more sensitive). minSpeechDurationMs: type: number format: double description: This is the minimum speech duration for VAD (50-2000ms). minSilenceDurationMs: type: number format: double description: This is the minimum silence duration for VAD (50-2000ms). required: - provider title: FallbackElevenLabsTranscriber FallbackGladiaTranscriberProvider: type: string enum: - gladia description: This is the transcription provider that will be used. title: FallbackGladiaTranscriberProvider FallbackGladiaTranscriberModel0: type: string enum: - fast - accurate - solaria-1 title: FallbackGladiaTranscriberModel0 FallbackGladiaTranscriberModel: oneOf: - $ref: '#/components/schemas/FallbackGladiaTranscriberModel0' description: This is the Gladia model that will be used. Default is 'fast' title: FallbackGladiaTranscriberModel FallbackGladiaTranscriberLanguageBehaviour0: type: string enum: - manual - automatic single language - automatic multiple languages title: FallbackGladiaTranscriberLanguageBehaviour0 FallbackGladiaTranscriberLanguageBehaviour: oneOf: - $ref: '#/components/schemas/FallbackGladiaTranscriberLanguageBehaviour0' description: >- Defines how the transcription model detects the audio language. Default value is 'automatic single language'. title: FallbackGladiaTranscriberLanguageBehaviour FallbackGladiaTranscriberLanguage: type: string enum: - af - sq - am - ar - hy - as - az - ba - eu - be - bn - bs - br - bg - ca - zh - hr - cs - da - nl - en - et - fo - fi - fr - gl - ka - de - el - gu - ht - ha - haw - he - hi - hu - is - id - it - ja - jv - kn - kk - km - ko - lo - la - lv - ln - lt - lb - mk - mg - ms - ml - mt - mi - mr - mn - my - ne - 'no' - nn - oc - ps - fa - pl - pt - pa - ro - ru - sa - sr - sn - sd - si - sk - sl - so - es - su - sw - sv - tl - tg - ta - tt - te - th - bo - tr - tk - uk - ur - uz - vi - cy - yi - yo description: >- Defines the language to use for the transcription. Required when languageBehaviour is 'manual'. title: FallbackGladiaTranscriberLanguage FallbackGladiaTranscriberLanguages: type: string enum: - af - sq - am - ar - hy - as - az - ba - eu - be - bn - bs - br - bg - ca - zh - hr - cs - da - nl - en - et - fo - fi - fr - gl - ka - de - el - gu - ht - ha - haw - he - hi - hu - is - id - it - ja - jv - kn - kk - km - ko - lo - la - lv - ln - lt - lb - mk - mg - ms - ml - mt - mi - mr - mn - my - ne - 'no' - nn - oc - ps - fa - pl - pt - pa - ro - ru - sa - sr - sn - sd - si - sk - sl - so - es - su - sw - sv - tl - tg - ta - tt - te - th - bo - tr - tk - uk - ur - uz - vi - cy - yi - yo description: >- Defines the languages to use for the transcription. Required when languageBehaviour is 'manual'. title: FallbackGladiaTranscriberLanguages GladiaVocabularyItemDTO: type: object properties: value: type: string description: The vocabulary word or phrase pronunciations: type: array items: type: string description: Alternative pronunciations for the vocabulary item intensity: type: number format: double description: Intensity for this specific vocabulary item (0.0 to 1.0) language: type: string description: Language code for this vocabulary item (ISO 639-1) required: - value title: GladiaVocabularyItemDTO GladiaCustomVocabularyConfigDtoVocabularyItems: oneOf: - type: string - $ref: '#/components/schemas/GladiaVocabularyItemDTO' title: GladiaCustomVocabularyConfigDtoVocabularyItems GladiaCustomVocabularyConfigDTO: type: object properties: vocabulary: type: array items: $ref: >- #/components/schemas/GladiaCustomVocabularyConfigDtoVocabularyItems description: >- Array of vocabulary items (strings or objects with value, pronunciations, intensity, language) defaultIntensity: type: number format: double default: 0.5 description: Default intensity for vocabulary items (0.0 to 1.0) required: - vocabulary title: GladiaCustomVocabularyConfigDTO FallbackGladiaTranscriberRegion: type: string enum: - us-west - eu-west description: Region for processing audio (us-west or eu-west) title: FallbackGladiaTranscriberRegion FallbackGladiaTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackGladiaTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/FallbackGladiaTranscriberModel' description: This is the Gladia model that will be used. Default is 'fast' languageBehaviour: $ref: '#/components/schemas/FallbackGladiaTranscriberLanguageBehaviour' description: >- Defines how the transcription model detects the audio language. Default value is 'automatic single language'. language: $ref: '#/components/schemas/FallbackGladiaTranscriberLanguage' description: >- Defines the language to use for the transcription. Required when languageBehaviour is 'manual'. languages: $ref: '#/components/schemas/FallbackGladiaTranscriberLanguages' description: >- Defines the languages to use for the transcription. Required when languageBehaviour is 'manual'. transcriptionHint: type: string description: >- Provides a custom vocabulary to the model to improve accuracy of transcribing context specific words, technical terms, names, etc. If empty, this argument is ignored. ⚠️ Warning ⚠️: Please be aware that the transcription_hint field has a character limit of 600. If you provide a transcription_hint longer than 600 characters, it will be automatically truncated to meet this limit. prosody: type: boolean description: >- If prosody is true, you will get a transcription that can contain prosodies i.e. (laugh) (giggles) (malefic laugh) (toss) (music)… Default value is false. audioEnhancer: type: boolean description: >- If true, audio will be pre-processed to improve accuracy but latency will increase. Default value is false. confidenceThreshold: type: number format: double description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 endpointing: type: number format: double description: >- Endpointing time in seconds - time to wait before considering speech ended speechThreshold: type: number format: double description: >- Speech threshold - sensitivity configuration for speech detection (0.0 to 1.0) customVocabularyEnabled: type: boolean description: Enable custom vocabulary for improved accuracy customVocabularyConfig: $ref: '#/components/schemas/GladiaCustomVocabularyConfigDTO' description: Custom vocabulary configuration region: $ref: '#/components/schemas/FallbackGladiaTranscriberRegion' description: Region for processing audio (us-west or eu-west) receivePartialTranscripts: type: boolean description: Enable partial transcripts for low-latency streaming transcription required: - provider title: FallbackGladiaTranscriber FallbackGoogleTranscriberProvider: type: string enum: - google description: This is the transcription provider that will be used. title: FallbackGoogleTranscriberProvider FallbackGoogleTranscriberModel: type: string enum: - gemini-3-flash-preview - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.0-flash-thinking-exp - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.0-flash-exp - gemini-2.0-flash-realtime-exp - gemini-1.5-flash - gemini-1.5-flash-002 - gemini-1.5-pro - gemini-1.5-pro-002 - gemini-1.0-pro description: This is the model that will be used for the transcription. title: FallbackGoogleTranscriberModel FallbackGoogleTranscriberLanguage: type: string enum: - Multilingual - Arabic - Bengali - Bulgarian - Chinese - Croatian - Czech - Danish - Dutch - English - Estonian - Finnish - French - German - Greek - Hebrew - Hindi - Hungarian - Indonesian - Italian - Japanese - Korean - Latvian - Lithuanian - Norwegian - Polish - Portuguese - Romanian - Russian - Serbian - Slovak - Slovenian - Spanish - Swahili - Swedish - Thai - Turkish - Ukrainian - Vietnamese description: This is the language that will be set for the transcription. title: FallbackGoogleTranscriberLanguage FallbackGoogleTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackGoogleTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/FallbackGoogleTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/FallbackGoogleTranscriberLanguage' description: This is the language that will be set for the transcription. required: - provider title: FallbackGoogleTranscriber FallbackTalkscriberTranscriberProvider: type: string enum: - talkscriber description: This is the transcription provider that will be used. title: FallbackTalkscriberTranscriberProvider FallbackTalkscriberTranscriberModel: type: string enum: - whisper description: This is the model that will be used for the transcription. title: FallbackTalkscriberTranscriberModel FallbackTalkscriberTranscriberLanguage: type: string enum: - en - zh - de - es - ru - ko - fr - ja - pt - tr - pl - ca - nl - ar - sv - it - id - hi - fi - vi - he - uk - el - ms - cs - ro - da - hu - ta - 'no' - th - ur - hr - bg - lt - la - mi - ml - cy - sk - te - fa - lv - bn - sr - az - sl - kn - et - mk - br - eu - is - hy - ne - mn - bs - kk - sq - sw - gl - mr - pa - si - km - sn - yo - so - af - oc - ka - be - tg - sd - gu - am - yi - lo - uz - fo - ht - ps - tk - nn - mt - sa - lb - my - bo - tl - mg - as - tt - haw - ln - ha - ba - jw - su - yue description: >- This is the language that will be set for the transcription. The list of languages Whisper supports can be found here: https://github.com/openai/whisper/blob/main/whisper/tokenizer.py title: FallbackTalkscriberTranscriberLanguage FallbackTalkscriberTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackTalkscriberTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/FallbackTalkscriberTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/FallbackTalkscriberTranscriberLanguage' description: >- This is the language that will be set for the transcription. The list of languages Whisper supports can be found here: https://github.com/openai/whisper/blob/main/whisper/tokenizer.py required: - provider title: FallbackTalkscriberTranscriber FallbackSpeechmaticsTranscriberProvider: type: string enum: - speechmatics description: This is the transcription provider that will be used. title: FallbackSpeechmaticsTranscriberProvider FallbackSpeechmaticsTranscriberModel: type: string enum: - default description: This is the model that will be used for the transcription. title: FallbackSpeechmaticsTranscriberModel FallbackSpeechmaticsTranscriberLanguage: type: string enum: - auto - ar - ar_en - ba - eu - be - bn - bg - yue - ca - hr - cs - da - nl - en - eo - et - fi - fr - gl - de - el - he - hi - hu - id - ia - ga - it - ja - ko - lv - lt - ms - en_ms - mt - cmn - cmn_en - mr - mn - 'no' - fa - pl - pt - ro - ru - sk - sl - es - en_es - sw - sv - tl - ta - en_ta - th - tr - uk - ur - ug - vi - cy title: FallbackSpeechmaticsTranscriberLanguage FallbackSpeechmaticsTranscriberOperatingPoint: type: string enum: - standard - enhanced default: enhanced description: >- This is the operating point for the transcription. Choose between `standard` for faster turnaround with strong accuracy or `enhanced` for highest accuracy when precision is critical. @default 'enhanced' title: FallbackSpeechmaticsTranscriberOperatingPoint FallbackSpeechmaticsTranscriberRegion: type: string enum: - eu - us default: eu description: >- This is the region for the Speechmatics API. Choose between EU (Europe) and US (United States) regions for lower latency and data sovereignty compliance. @default 'eu' title: FallbackSpeechmaticsTranscriberRegion SpeechmaticsCustomVocabularyItem: type: object properties: content: type: string description: The word or phrase to add to the custom vocabulary. soundsLike: type: array items: type: string description: >- Alternative phonetic representations of how the word might sound. This helps recognition when the word might be pronounced differently. required: - content title: SpeechmaticsCustomVocabularyItem FallbackSpeechmaticsTranscriberNumeralStyle: type: string enum: - written - spoken default: written description: >- This controls how numbers, dates, currencies, and other entities are formatted in the transcription output. @default 'written' title: FallbackSpeechmaticsTranscriberNumeralStyle FallbackSpeechmaticsTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackSpeechmaticsTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/FallbackSpeechmaticsTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/FallbackSpeechmaticsTranscriberLanguage' operatingPoint: $ref: '#/components/schemas/FallbackSpeechmaticsTranscriberOperatingPoint' description: >- This is the operating point for the transcription. Choose between `standard` for faster turnaround with strong accuracy or `enhanced` for highest accuracy when precision is critical. @default 'enhanced' region: $ref: '#/components/schemas/FallbackSpeechmaticsTranscriberRegion' description: >- This is the region for the Speechmatics API. Choose between EU (Europe) and US (United States) regions for lower latency and data sovereignty compliance. @default 'eu' enableDiarization: type: boolean default: false description: >- This enables speaker diarization, which identifies and separates speakers in the transcription. Essential for multi-speaker conversations and conference calls. @default false maxDelay: type: number format: double default: 3000 description: >- This sets the maximum delay in milliseconds for partial transcripts. Balances latency and accuracy. @default 3000 customVocabulary: type: array items: $ref: '#/components/schemas/SpeechmaticsCustomVocabularyItem' numeralStyle: $ref: '#/components/schemas/FallbackSpeechmaticsTranscriberNumeralStyle' description: >- This controls how numbers, dates, currencies, and other entities are formatted in the transcription output. @default 'written' endOfTurnSensitivity: type: number format: double default: 0.5 description: >- This is the sensitivity level for end-of-turn detection, which determines when a speaker has finished talking. Higher values are more sensitive. @default 0.5 removeDisfluencies: type: boolean default: false description: >- This enables removal of disfluencies (um, uh) from the transcript to create cleaner, more professional output. This is only supported for the English language transcriber. @default false minimumSpeechDuration: type: number format: double default: 0 description: >- This is the minimum duration in seconds for speech segments. Shorter segments will be filtered out. Helps remove noise and improve accuracy. @default 0.0 required: - provider - customVocabulary title: FallbackSpeechmaticsTranscriber FallbackOpenAiTranscriberProvider: type: string enum: - openai description: This is the transcription provider that will be used. title: FallbackOpenAiTranscriberProvider FallbackOpenAiTranscriberModel: type: string enum: - gpt-4o-transcribe - gpt-4o-mini-transcribe description: This is the model that will be used for the transcription. title: FallbackOpenAiTranscriberModel FallbackOpenAiTranscriberLanguage: type: string enum: - af - ar - hy - az - be - bs - bg - ca - zh - hr - cs - da - nl - en - et - fi - fr - gl - de - el - he - hi - hu - is - id - it - ja - kn - kk - ko - lv - lt - mk - ms - mr - mi - ne - 'no' - fa - pl - pt - ro - ru - sr - sk - sl - es - sw - sv - tl - ta - th - tr - uk - ur - vi - cy description: This is the language that will be set for the transcription. title: FallbackOpenAiTranscriberLanguage FallbackOpenAITranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackOpenAiTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/FallbackOpenAiTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/FallbackOpenAiTranscriberLanguage' description: This is the language that will be set for the transcription. required: - provider - model title: FallbackOpenAITranscriber FallbackCartesiaTranscriberProvider: type: string enum: - cartesia title: FallbackCartesiaTranscriberProvider FallbackCartesiaTranscriberModel: type: string enum: - ink-whisper title: FallbackCartesiaTranscriberModel FallbackCartesiaTranscriberLanguage: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu title: FallbackCartesiaTranscriberLanguage FallbackCartesiaTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackCartesiaTranscriberProvider' model: $ref: '#/components/schemas/FallbackCartesiaTranscriberModel' language: $ref: '#/components/schemas/FallbackCartesiaTranscriberLanguage' required: - provider title: FallbackCartesiaTranscriber FallbackSonioxTranscriberProvider: type: string enum: - soniox title: FallbackSonioxTranscriberProvider FallbackSonioxTranscriberModel: type: string enum: - stt-rt-v4 description: The Soniox model to use for transcription. title: FallbackSonioxTranscriberModel FallbackSonioxTranscriberLanguage: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu description: >- The language for transcription. Uses ISO 639-1 codes. Soniox supports 60+ languages with a single universal model. title: FallbackSonioxTranscriberLanguage FallbackSonioxTranscriber: type: object properties: provider: $ref: '#/components/schemas/FallbackSonioxTranscriberProvider' model: $ref: '#/components/schemas/FallbackSonioxTranscriberModel' description: The Soniox model to use for transcription. language: $ref: '#/components/schemas/FallbackSonioxTranscriberLanguage' description: >- The language for transcription. Uses ISO 639-1 codes. Soniox supports 60+ languages with a single universal model. languageHintsStrict: type: boolean description: >- When enabled, restricts transcription to the language specified in the language field. When disabled, the model can detect and transcribe any of 60+ supported languages. Defaults to true. maxEndpointDelayMs: type: number format: double description: >- Maximum delay in milliseconds between when the speaker stops and when the endpoint is detected. Lower values mean faster turn-taking but more false endpoints. Range: 500-3000. Default: 500. customVocabulary: type: array items: type: string description: >- Custom vocabulary terms to boost recognition accuracy. Useful for brand names, product names, and domain-specific terminology. Maps to Soniox context.terms. required: - provider title: FallbackSonioxTranscriber FallbackTranscriberPlanTranscribersItems: oneOf: - $ref: '#/components/schemas/FallbackAssemblyAITranscriber' - $ref: '#/components/schemas/FallbackAzureSpeechTranscriber' - $ref: '#/components/schemas/FallbackCustomTranscriber' - $ref: '#/components/schemas/FallbackDeepgramTranscriber' - $ref: '#/components/schemas/FallbackElevenLabsTranscriber' - $ref: '#/components/schemas/FallbackGladiaTranscriber' - $ref: '#/components/schemas/FallbackGoogleTranscriber' - $ref: '#/components/schemas/FallbackTalkscriberTranscriber' - $ref: '#/components/schemas/FallbackSpeechmaticsTranscriber' - $ref: '#/components/schemas/FallbackOpenAITranscriber' - $ref: '#/components/schemas/FallbackCartesiaTranscriber' - $ref: '#/components/schemas/FallbackSonioxTranscriber' title: FallbackTranscriberPlanTranscribersItems FallbackTranscriberPlan: type: object properties: transcribers: type: array items: $ref: '#/components/schemas/FallbackTranscriberPlanTranscribersItems' required: - transcribers title: FallbackTranscriberPlan AssemblyAITranscriber: type: object properties: provider: $ref: '#/components/schemas/AssemblyAiTranscriberProvider' description: This is the transcription provider that will be used. language: $ref: '#/components/schemas/AssemblyAiTranscriberLanguage' description: This is the language that will be set for the transcription. confidenceThreshold: type: number format: double description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 formatTurns: type: boolean description: |- This enables formatting of transcripts. @default true endOfTurnConfidenceThreshold: type: number format: double description: >- This is the end of turn confidence threshold. The minimum confidence that the end of turn is detected. Note: Only used if startSpeakingPlan.smartEndpointingPlan is not set. @min 0 @max 1 @default 0.7 minEndOfTurnSilenceWhenConfident: type: number format: double description: >- This is the minimum end of turn silence when confident in milliseconds. Note: Only used if startSpeakingPlan.smartEndpointingPlan is not set. @default 160 wordFinalizationMaxWaitTime: type: number format: double maxTurnSilence: type: number format: double description: >- This is the maximum turn silence time in milliseconds. Note: Only used if startSpeakingPlan.smartEndpointingPlan is not set. @default 400 vadAssistedEndpointingEnabled: type: boolean description: >- Use VAD to assist with endpointing decisions from the transcriber. When enabled, transcriber endpointing will be buffered if VAD detects the user is still speaking, preventing premature turn-taking. When disabled, transcriber endpointing will be used immediately regardless of VAD state, allowing for quicker but more aggressive turn-taking. Note: Only used if startSpeakingPlan.smartEndpointingPlan is not set. @default true speechModel: $ref: '#/components/schemas/AssemblyAiTranscriberSpeechModel' description: >- This is the speech model used for the streaming session. Note: Keyterms prompting is not supported with multilingual streaming. @default 'universal-streaming-english' realtimeUrl: type: string description: The WebSocket URL that the transcriber connects to. wordBoost: type: array items: type: string description: Add up to 2500 characters of custom vocabulary. keytermsPrompt: type: array items: type: string description: >- Keyterms prompting improves recognition accuracy for specific words and phrases. Can include up to 100 keyterms, each up to 50 characters. Costs an additional $0.04/hour when enabled. endUtteranceSilenceThreshold: type: number format: double description: The duration of the end utterance silence threshold in milliseconds. disablePartialTranscripts: type: boolean description: >- Disable partial transcripts. Set to `true` to not receive partial transcripts. Defaults to `false`. fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider title: AssemblyAITranscriber AzureSpeechTranscriberProvider: type: string enum: - azure description: This is the transcription provider that will be used. title: AzureSpeechTranscriberProvider AzureSpeechTranscriberLanguage: type: string enum: - af-ZA - am-ET - ar-AE - ar-BH - ar-DZ - ar-EG - ar-IL - ar-IQ - ar-JO - ar-KW - ar-LB - ar-LY - ar-MA - ar-OM - ar-PS - ar-QA - ar-SA - ar-SY - ar-TN - ar-YE - az-AZ - bg-BG - bn-IN - bs-BA - ca-ES - cs-CZ - cy-GB - da-DK - de-AT - de-CH - de-DE - el-GR - en-AU - en-CA - en-GB - en-GH - en-HK - en-IE - en-IN - en-KE - en-NG - en-NZ - en-PH - en-SG - en-TZ - en-US - en-ZA - es-AR - es-BO - es-CL - es-CO - es-CR - es-CU - es-DO - es-EC - es-ES - es-GQ - es-GT - es-HN - es-MX - es-NI - es-PA - es-PE - es-PR - es-PY - es-SV - es-US - es-UY - es-VE - et-EE - eu-ES - fa-IR - fi-FI - fil-PH - fr-BE - fr-CA - fr-CH - fr-FR - ga-IE - gl-ES - gu-IN - he-IL - hi-IN - hr-HR - hu-HU - hy-AM - id-ID - is-IS - it-CH - it-IT - ja-JP - jv-ID - ka-GE - kk-KZ - km-KH - kn-IN - ko-KR - lo-LA - lt-LT - lv-LV - mk-MK - ml-IN - mn-MN - mr-IN - ms-MY - mt-MT - my-MM - nb-NO - ne-NP - nl-BE - nl-NL - pa-IN - pl-PL - ps-AF - pt-BR - pt-PT - ro-RO - ru-RU - si-LK - sk-SK - sl-SI - so-SO - sq-AL - sr-RS - sv-SE - sw-KE - sw-TZ - ta-IN - te-IN - th-TH - tr-TR - uk-UA - ur-IN - uz-UZ - vi-VN - wuu-CN - yue-CN - zh-CN - zh-CN-shandong - zh-CN-sichuan - zh-HK - zh-TW - zu-ZA description: >- This is the language that will be set for the transcription. The list of languages Azure supports can be found here: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=stt title: AzureSpeechTranscriberLanguage AzureSpeechTranscriberSegmentationStrategy: type: string enum: - Default - Time - Semantic description: >- Controls how phrase boundaries are detected, enabling either simple time/silence heuristics or more advanced semantic segmentation. title: AzureSpeechTranscriberSegmentationStrategy AzureSpeechTranscriber: type: object properties: provider: $ref: '#/components/schemas/AzureSpeechTranscriberProvider' description: This is the transcription provider that will be used. language: $ref: '#/components/schemas/AzureSpeechTranscriberLanguage' description: >- This is the language that will be set for the transcription. The list of languages Azure supports can be found here: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=stt segmentationStrategy: $ref: '#/components/schemas/AzureSpeechTranscriberSegmentationStrategy' description: >- Controls how phrase boundaries are detected, enabling either simple time/silence heuristics or more advanced semantic segmentation. segmentationSilenceTimeoutMs: type: number format: double description: >- Duration of detected silence after which the service finalizes a phrase. Configure to adjust sensitivity to pauses in speech. segmentationMaximumTimeMs: type: number format: double description: >- Maximum duration a segment can reach before being cut off when using time-based segmentation. fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider title: AzureSpeechTranscriber CustomTranscriberProvider: type: string enum: - custom-transcriber description: >- This is the transcription provider that will be used. Use `custom-transcriber` for providers that are not natively supported. title: CustomTranscriberProvider CustomTranscriber: type: object properties: provider: $ref: '#/components/schemas/CustomTranscriberProvider' description: >- This is the transcription provider that will be used. Use `custom-transcriber` for providers that are not natively supported. server: $ref: '#/components/schemas/Server' description: >- This is where the transcription request will be sent. Usage: 1. Vapi will initiate a websocket connection with `server.url`. 2. Vapi will send an initial text frame with the sample rate. Format: ``` { "type": "start", "encoding": "linear16", // 16-bit raw PCM format "container": "raw", "sampleRate": {{sampleRate}}, "channels": 2 // customer is channel 0, assistant is channel 1 } ``` 3. Vapi will send the audio data in 16-bit raw PCM format as binary frames. 4. You can read the messages something like this: ``` ws.on('message', (data, isBinary) => { if (isBinary) { pcmBuffer = Buffer.concat([pcmBuffer, data]); console.log(`Received PCM data, buffer size: ${pcmBuffer.length}`); } else { console.log('Received message:', JSON.parse(data.toString())); } }); ``` 5. You will respond with transcriptions as you have them. Format: ``` { "type": "transcriber-response", "transcription": "Hello, world!", "channel": "customer" | "assistant" } ``` fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider - server title: CustomTranscriber DeepgramTranscriberProvider: type: string enum: - deepgram description: This is the transcription provider that will be used. title: DeepgramTranscriberProvider DeepgramTranscriber: type: object properties: provider: $ref: '#/components/schemas/DeepgramTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/DeepgramTranscriberModel' description: >- This is the Deepgram model that will be used. A list of models can be found here: https://developers.deepgram.com/docs/models-languages-overview language: $ref: '#/components/schemas/DeepgramTranscriberLanguage' description: >- This is the language that will be set for the transcription. The list of languages Deepgram supports can be found here: https://developers.deepgram.com/docs/models-languages-overview smartFormat: type: boolean description: >- This will be use smart format option provided by Deepgram. It's default disabled because it can sometimes format numbers as times but it's getting better. mipOptOut: type: boolean default: false description: >- If set to true, this will add mip_opt_out=true as a query parameter of all API requests. See https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#want-to-opt-out This will only be used if you are using your own Deepgram API key. @default false numerals: type: boolean description: >- If set to true, this will cause deepgram to convert spoken numbers to literal numerals. For example, "my phone number is nine-seven-two..." would become "my phone number is 972..." @default false profanityFilter: type: boolean description: >- If set to true, Deepgram will replace profanity in transcripts with surrounding asterisks, e.g. "f***". @default false confidenceThreshold: type: number format: double description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 eagerEotThreshold: type: number format: double description: >- Eager end-of-turn confidence required to fire a eager end-of-turn event. Setting a value here will enable EagerEndOfTurn and SpeechResumed events. It is disabled by default. Only used with Flux models. eotThreshold: type: number format: double description: >- End-of-turn confidence required to finish a turn. Only used with Flux models. @default 0.7 eotTimeoutMs: type: number format: double description: >- A turn will be finished when this much time has passed after speech, regardless of EOT confidence. Only used with Flux models. @default 5000 keywords: type: array items: type: string description: >- These keywords are passed to the transcription model to help it pick up use-case specific words. Anything that may not be a common word, like your company name, should be added here. keyterm: type: array items: type: string description: >- Keyterm Prompting allows you improve Keyword Recall Rate (KRR) for important keyterms or phrases up to 90%. endpointing: type: number format: double description: >- This is the timeout after which Deepgram will send transcription on user silence. You can read in-depth documentation here: https://developers.deepgram.com/docs/endpointing. Here are the most important bits: - Defaults to 10. This is recommended for most use cases to optimize for latency. - 10 can cause some missing transcriptions since because of the shorter context. This mostly happens for one-word utterances. For those uses cases, it's recommended to try 300. It will add a bit of latency but the quality and reliability of the experience will be better. - If neither 10 nor 300 work, contact support@vapi.ai and we'll find another solution. @default 10 fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider title: DeepgramTranscriber ElevenLabsTranscriberProvider: type: string enum: - 11labs description: This is the transcription provider that will be used. title: ElevenLabsTranscriberProvider ElevenLabsTranscriberModel0: type: string enum: - scribe_v1 - scribe_v2 - scribe_v2_realtime title: ElevenLabsTranscriberModel0 ElevenLabsTranscriberModel: oneOf: - $ref: '#/components/schemas/ElevenLabsTranscriberModel0' description: This is the model that will be used for the transcription. title: ElevenLabsTranscriberModel ElevenLabsTranscriberLanguage: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu description: This is the language that will be used for the transcription. title: ElevenLabsTranscriberLanguage ElevenLabsTranscriber: type: object properties: provider: $ref: '#/components/schemas/ElevenLabsTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/ElevenLabsTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/ElevenLabsTranscriberLanguage' description: This is the language that will be used for the transcription. silenceThresholdSeconds: type: number format: double description: >- This is the number of seconds of silence before VAD commits (0.3-3.0). confidenceThreshold: type: number format: double description: >- This is the VAD sensitivity (0.1-0.9, lower indicates more sensitive). minSpeechDurationMs: type: number format: double description: This is the minimum speech duration for VAD (50-2000ms). minSilenceDurationMs: type: number format: double description: This is the minimum silence duration for VAD (50-2000ms). fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider title: ElevenLabsTranscriber GladiaTranscriberProvider: type: string enum: - gladia description: This is the transcription provider that will be used. title: GladiaTranscriberProvider GladiaTranscriberModel0: type: string enum: - fast - accurate - solaria-1 title: GladiaTranscriberModel0 GladiaTranscriberModel: oneOf: - $ref: '#/components/schemas/GladiaTranscriberModel0' description: This is the Gladia model that will be used. Default is 'fast' title: GladiaTranscriberModel GladiaTranscriberLanguageBehaviour0: type: string enum: - manual - automatic single language - automatic multiple languages title: GladiaTranscriberLanguageBehaviour0 GladiaTranscriberLanguageBehaviour: oneOf: - $ref: '#/components/schemas/GladiaTranscriberLanguageBehaviour0' description: >- Defines how the transcription model detects the audio language. Default value is 'automatic single language'. title: GladiaTranscriberLanguageBehaviour GladiaTranscriberLanguage: type: string enum: - af - sq - am - ar - hy - as - az - ba - eu - be - bn - bs - br - bg - ca - zh - hr - cs - da - nl - en - et - fo - fi - fr - gl - ka - de - el - gu - ht - ha - haw - he - hi - hu - is - id - it - ja - jv - kn - kk - km - ko - lo - la - lv - ln - lt - lb - mk - mg - ms - ml - mt - mi - mr - mn - my - ne - 'no' - nn - oc - ps - fa - pl - pt - pa - ro - ru - sa - sr - sn - sd - si - sk - sl - so - es - su - sw - sv - tl - tg - ta - tt - te - th - bo - tr - tk - uk - ur - uz - vi - cy - yi - yo description: >- Defines the language to use for the transcription. Required when languageBehaviour is 'manual'. title: GladiaTranscriberLanguage GladiaTranscriberLanguages: type: string enum: - af - sq - am - ar - hy - as - az - ba - eu - be - bn - bs - br - bg - ca - zh - hr - cs - da - nl - en - et - fo - fi - fr - gl - ka - de - el - gu - ht - ha - haw - he - hi - hu - is - id - it - ja - jv - kn - kk - km - ko - lo - la - lv - ln - lt - lb - mk - mg - ms - ml - mt - mi - mr - mn - my - ne - 'no' - nn - oc - ps - fa - pl - pt - pa - ro - ru - sa - sr - sn - sd - si - sk - sl - so - es - su - sw - sv - tl - tg - ta - tt - te - th - bo - tr - tk - uk - ur - uz - vi - cy - yi - yo description: >- Defines the languages to use for the transcription. Required when languageBehaviour is 'manual'. title: GladiaTranscriberLanguages GladiaTranscriberRegion: type: string enum: - us-west - eu-west description: Region for processing audio (us-west or eu-west) title: GladiaTranscriberRegion GladiaTranscriber: type: object properties: provider: $ref: '#/components/schemas/GladiaTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/GladiaTranscriberModel' description: This is the Gladia model that will be used. Default is 'fast' languageBehaviour: $ref: '#/components/schemas/GladiaTranscriberLanguageBehaviour' description: >- Defines how the transcription model detects the audio language. Default value is 'automatic single language'. language: $ref: '#/components/schemas/GladiaTranscriberLanguage' description: >- Defines the language to use for the transcription. Required when languageBehaviour is 'manual'. languages: $ref: '#/components/schemas/GladiaTranscriberLanguages' description: >- Defines the languages to use for the transcription. Required when languageBehaviour is 'manual'. transcriptionHint: type: string description: >- Provides a custom vocabulary to the model to improve accuracy of transcribing context specific words, technical terms, names, etc. If empty, this argument is ignored. ⚠️ Warning ⚠️: Please be aware that the transcription_hint field has a character limit of 600. If you provide a transcription_hint longer than 600 characters, it will be automatically truncated to meet this limit. prosody: type: boolean description: >- If prosody is true, you will get a transcription that can contain prosodies i.e. (laugh) (giggles) (malefic laugh) (toss) (music)… Default value is false. audioEnhancer: type: boolean description: >- If true, audio will be pre-processed to improve accuracy but latency will increase. Default value is false. confidenceThreshold: type: number format: double description: |- Transcripts below this confidence threshold will be discarded. @default 0.4 endpointing: type: number format: double description: >- Endpointing time in seconds - time to wait before considering speech ended speechThreshold: type: number format: double description: >- Speech threshold - sensitivity configuration for speech detection (0.0 to 1.0) customVocabularyEnabled: type: boolean description: Enable custom vocabulary for improved accuracy customVocabularyConfig: $ref: '#/components/schemas/GladiaCustomVocabularyConfigDTO' description: Custom vocabulary configuration region: $ref: '#/components/schemas/GladiaTranscriberRegion' description: Region for processing audio (us-west or eu-west) receivePartialTranscripts: type: boolean description: Enable partial transcripts for low-latency streaming transcription fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider title: GladiaTranscriber GoogleTranscriberProvider: type: string enum: - google description: This is the transcription provider that will be used. title: GoogleTranscriberProvider GoogleTranscriberModel: type: string enum: - gemini-3-flash-preview - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.0-flash-thinking-exp - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.0-flash-exp - gemini-2.0-flash-realtime-exp - gemini-1.5-flash - gemini-1.5-flash-002 - gemini-1.5-pro - gemini-1.5-pro-002 - gemini-1.0-pro description: This is the model that will be used for the transcription. title: GoogleTranscriberModel GoogleTranscriberLanguage: type: string enum: - Multilingual - Arabic - Bengali - Bulgarian - Chinese - Croatian - Czech - Danish - Dutch - English - Estonian - Finnish - French - German - Greek - Hebrew - Hindi - Hungarian - Indonesian - Italian - Japanese - Korean - Latvian - Lithuanian - Norwegian - Polish - Portuguese - Romanian - Russian - Serbian - Slovak - Slovenian - Spanish - Swahili - Swedish - Thai - Turkish - Ukrainian - Vietnamese description: This is the language that will be set for the transcription. title: GoogleTranscriberLanguage GoogleTranscriber: type: object properties: provider: $ref: '#/components/schemas/GoogleTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/GoogleTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/GoogleTranscriberLanguage' description: This is the language that will be set for the transcription. fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider title: GoogleTranscriber SpeechmaticsTranscriberProvider: type: string enum: - speechmatics description: This is the transcription provider that will be used. title: SpeechmaticsTranscriberProvider SpeechmaticsTranscriberModel: type: string enum: - default description: This is the model that will be used for the transcription. title: SpeechmaticsTranscriberModel SpeechmaticsTranscriberLanguage: type: string enum: - auto - ar - ar_en - ba - eu - be - bn - bg - yue - ca - hr - cs - da - nl - en - eo - et - fi - fr - gl - de - el - he - hi - hu - id - ia - ga - it - ja - ko - lv - lt - ms - en_ms - mt - cmn - cmn_en - mr - mn - 'no' - fa - pl - pt - ro - ru - sk - sl - es - en_es - sw - sv - tl - ta - en_ta - th - tr - uk - ur - ug - vi - cy title: SpeechmaticsTranscriberLanguage SpeechmaticsTranscriberOperatingPoint: type: string enum: - standard - enhanced default: enhanced description: >- This is the operating point for the transcription. Choose between `standard` for faster turnaround with strong accuracy or `enhanced` for highest accuracy when precision is critical. @default 'enhanced' title: SpeechmaticsTranscriberOperatingPoint SpeechmaticsTranscriberRegion: type: string enum: - eu - us default: eu description: >- This is the region for the Speechmatics API. Choose between EU (Europe) and US (United States) regions for lower latency and data sovereignty compliance. @default 'eu' title: SpeechmaticsTranscriberRegion SpeechmaticsTranscriberNumeralStyle: type: string enum: - written - spoken default: written description: >- This controls how numbers, dates, currencies, and other entities are formatted in the transcription output. @default 'written' title: SpeechmaticsTranscriberNumeralStyle SpeechmaticsTranscriber: type: object properties: provider: $ref: '#/components/schemas/SpeechmaticsTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/SpeechmaticsTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/SpeechmaticsTranscriberLanguage' operatingPoint: $ref: '#/components/schemas/SpeechmaticsTranscriberOperatingPoint' description: >- This is the operating point for the transcription. Choose between `standard` for faster turnaround with strong accuracy or `enhanced` for highest accuracy when precision is critical. @default 'enhanced' region: $ref: '#/components/schemas/SpeechmaticsTranscriberRegion' description: >- This is the region for the Speechmatics API. Choose between EU (Europe) and US (United States) regions for lower latency and data sovereignty compliance. @default 'eu' enableDiarization: type: boolean default: false description: >- This enables speaker diarization, which identifies and separates speakers in the transcription. Essential for multi-speaker conversations and conference calls. @default false maxDelay: type: number format: double default: 3000 description: >- This sets the maximum delay in milliseconds for partial transcripts. Balances latency and accuracy. @default 3000 customVocabulary: type: array items: $ref: '#/components/schemas/SpeechmaticsCustomVocabularyItem' numeralStyle: $ref: '#/components/schemas/SpeechmaticsTranscriberNumeralStyle' description: >- This controls how numbers, dates, currencies, and other entities are formatted in the transcription output. @default 'written' endOfTurnSensitivity: type: number format: double default: 0.5 description: >- This is the sensitivity level for end-of-turn detection, which determines when a speaker has finished talking. Higher values are more sensitive. @default 0.5 removeDisfluencies: type: boolean default: false description: >- This enables removal of disfluencies (um, uh) from the transcript to create cleaner, more professional output. This is only supported for the English language transcriber. @default false minimumSpeechDuration: type: number format: double default: 0 description: >- This is the minimum duration in seconds for speech segments. Shorter segments will be filtered out. Helps remove noise and improve accuracy. @default 0.0 fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider - customVocabulary title: SpeechmaticsTranscriber TalkscriberTranscriberProvider: type: string enum: - talkscriber description: This is the transcription provider that will be used. title: TalkscriberTranscriberProvider TalkscriberTranscriberModel: type: string enum: - whisper description: This is the model that will be used for the transcription. title: TalkscriberTranscriberModel TalkscriberTranscriberLanguage: type: string enum: - en - zh - de - es - ru - ko - fr - ja - pt - tr - pl - ca - nl - ar - sv - it - id - hi - fi - vi - he - uk - el - ms - cs - ro - da - hu - ta - 'no' - th - ur - hr - bg - lt - la - mi - ml - cy - sk - te - fa - lv - bn - sr - az - sl - kn - et - mk - br - eu - is - hy - ne - mn - bs - kk - sq - sw - gl - mr - pa - si - km - sn - yo - so - af - oc - ka - be - tg - sd - gu - am - yi - lo - uz - fo - ht - ps - tk - nn - mt - sa - lb - my - bo - tl - mg - as - tt - haw - ln - ha - ba - jw - su - yue description: >- This is the language that will be set for the transcription. The list of languages Whisper supports can be found here: https://github.com/openai/whisper/blob/main/whisper/tokenizer.py title: TalkscriberTranscriberLanguage TalkscriberTranscriber: type: object properties: provider: $ref: '#/components/schemas/TalkscriberTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/TalkscriberTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/TalkscriberTranscriberLanguage' description: >- This is the language that will be set for the transcription. The list of languages Whisper supports can be found here: https://github.com/openai/whisper/blob/main/whisper/tokenizer.py fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider title: TalkscriberTranscriber OpenAiTranscriberProvider: type: string enum: - openai description: This is the transcription provider that will be used. title: OpenAiTranscriberProvider OpenAiTranscriberModel: type: string enum: - gpt-4o-transcribe - gpt-4o-mini-transcribe description: This is the model that will be used for the transcription. title: OpenAiTranscriberModel OpenAiTranscriberLanguage: type: string enum: - af - ar - hy - az - be - bs - bg - ca - zh - hr - cs - da - nl - en - et - fi - fr - gl - de - el - he - hi - hu - is - id - it - ja - kn - kk - ko - lv - lt - mk - ms - mr - mi - ne - 'no' - fa - pl - pt - ro - ru - sr - sk - sl - es - sw - sv - tl - ta - th - tr - uk - ur - vi - cy description: This is the language that will be set for the transcription. title: OpenAiTranscriberLanguage OpenAITranscriber: type: object properties: provider: $ref: '#/components/schemas/OpenAiTranscriberProvider' description: This is the transcription provider that will be used. model: $ref: '#/components/schemas/OpenAiTranscriberModel' description: This is the model that will be used for the transcription. language: $ref: '#/components/schemas/OpenAiTranscriberLanguage' description: This is the language that will be set for the transcription. fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider - model title: OpenAITranscriber CartesiaTranscriberProvider: type: string enum: - cartesia title: CartesiaTranscriberProvider CartesiaTranscriberModel: type: string enum: - ink-whisper title: CartesiaTranscriberModel CartesiaTranscriberLanguage: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu title: CartesiaTranscriberLanguage CartesiaTranscriber: type: object properties: provider: $ref: '#/components/schemas/CartesiaTranscriberProvider' model: $ref: '#/components/schemas/CartesiaTranscriberModel' language: $ref: '#/components/schemas/CartesiaTranscriberLanguage' fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider title: CartesiaTranscriber SonioxTranscriberProvider: type: string enum: - soniox title: SonioxTranscriberProvider SonioxTranscriberModel: type: string enum: - stt-rt-v4 description: The Soniox model to use for transcription. title: SonioxTranscriberModel SonioxTranscriberLanguage: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu description: >- The language for transcription. Uses ISO 639-1 codes. Soniox supports 60+ languages with a single universal model. title: SonioxTranscriberLanguage SonioxTranscriber: type: object properties: provider: $ref: '#/components/schemas/SonioxTranscriberProvider' model: $ref: '#/components/schemas/SonioxTranscriberModel' description: The Soniox model to use for transcription. language: $ref: '#/components/schemas/SonioxTranscriberLanguage' description: >- The language for transcription. Uses ISO 639-1 codes. Soniox supports 60+ languages with a single universal model. languageHintsStrict: type: boolean description: >- When enabled, restricts transcription to the language specified in the language field. When disabled, the model can detect and transcribe any of 60+ supported languages. Defaults to true. maxEndpointDelayMs: type: number format: double description: >- Maximum delay in milliseconds between when the speaker stops and when the endpoint is detected. Lower values mean faster turn-taking but more false endpoints. Range: 500-3000. Default: 500. customVocabulary: type: array items: type: string description: >- Custom vocabulary terms to boost recognition accuracy. Useful for brand names, product names, and domain-specific terminology. Maps to Soniox context.terms. fallbackPlan: $ref: '#/components/schemas/FallbackTranscriberPlan' description: >- This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails. required: - provider title: SonioxTranscriber CreateAssistantDtoTranscriber: oneOf: - $ref: '#/components/schemas/AssemblyAITranscriber' - $ref: '#/components/schemas/AzureSpeechTranscriber' - $ref: '#/components/schemas/CustomTranscriber' - $ref: '#/components/schemas/DeepgramTranscriber' - $ref: '#/components/schemas/ElevenLabsTranscriber' - $ref: '#/components/schemas/GladiaTranscriber' - $ref: '#/components/schemas/GoogleTranscriber' - $ref: '#/components/schemas/SpeechmaticsTranscriber' - $ref: '#/components/schemas/TalkscriberTranscriber' - $ref: '#/components/schemas/OpenAITranscriber' - $ref: '#/components/schemas/CartesiaTranscriber' - $ref: '#/components/schemas/SonioxTranscriber' description: These are the options for the assistant's transcriber. title: CreateAssistantDtoTranscriber ToolMessageStartContentsItems: oneOf: - $ref: '#/components/schemas/TextContent' title: ToolMessageStartContentsItems ToolMessageStartType: type: string enum: - request-start description: >- This message is triggered when the tool call starts. This message is never triggered for async tools. If this message is not provided, one of the default filler messages "Hold on a sec", "One moment", "Just a sec", "Give me a moment" or "This'll just take a sec" will be used. title: ToolMessageStartType ConditionOperator: type: string enum: - eq - neq - gt - gte - lt - lte description: This is the operator you want to use to compare the parameter and value. title: ConditionOperator Condition: type: object properties: operator: $ref: '#/components/schemas/ConditionOperator' description: >- This is the operator you want to use to compare the parameter and value. param: type: string description: This is the name of the parameter that you want to check. value: type: string description: This is the value you want to compare against the parameter. required: - operator - param - value title: Condition ToolMessageStart: type: object properties: contents: type: array items: $ref: '#/components/schemas/ToolMessageStartContentsItems' description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/ToolMessageStartType' description: >- This message is triggered when the tool call starts. This message is never triggered for async tools. If this message is not provided, one of the default filler messages "Hold on a sec", "One moment", "Just a sec", "Give me a moment" or "This'll just take a sec" will be used. blocking: type: boolean default: false description: >- This is an optional boolean that if true, the tool call will only trigger after the message is spoken. Default is false. @default false content: type: string description: >- This is the content that the assistant says when this message is triggered. conditions: type: array items: $ref: '#/components/schemas/Condition' description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. required: - type title: ToolMessageStart ToolMessageCompleteContentsItems: oneOf: - $ref: '#/components/schemas/TextContent' title: ToolMessageCompleteContentsItems ToolMessageCompleteType: type: string enum: - request-complete description: >- This message is triggered when the tool call is complete. This message is triggered immediately without waiting for your server to respond for async tool calls. If this message is not provided, the model will be requested to respond. If this message is provided, only this message will be spoken and the model will not be requested to come up with a response. It's an exclusive OR. title: ToolMessageCompleteType ToolMessageCompleteRole: type: string enum: - assistant - system description: >- This is optional and defaults to "assistant". When role=assistant, `content` is said out loud. When role=system, `content` is passed to the model in a system message. Example: system: default one assistant: user: assistant: user: assistant: user: assistant: tool called tool: your server response <--- system prompt as hint ---> model generates response which is spoken This is useful when you want to provide a hint to the model about what to say next. title: ToolMessageCompleteRole ToolMessageComplete: type: object properties: contents: type: array items: $ref: '#/components/schemas/ToolMessageCompleteContentsItems' description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/ToolMessageCompleteType' description: >- This message is triggered when the tool call is complete. This message is triggered immediately without waiting for your server to respond for async tool calls. If this message is not provided, the model will be requested to respond. If this message is provided, only this message will be spoken and the model will not be requested to come up with a response. It's an exclusive OR. role: $ref: '#/components/schemas/ToolMessageCompleteRole' description: >- This is optional and defaults to "assistant". When role=assistant, `content` is said out loud. When role=system, `content` is passed to the model in a system message. Example: system: default one assistant: user: assistant: user: assistant: user: assistant: tool called tool: your server response <--- system prompt as hint ---> model generates response which is spoken This is useful when you want to provide a hint to the model about what to say next. endCallAfterSpokenEnabled: type: boolean description: >- This is an optional boolean that if true, the call will end after the message is spoken. Default is false. This is ignored if `role` is set to `system`. @default false content: type: string description: >- This is the content that the assistant says when this message is triggered. conditions: type: array items: $ref: '#/components/schemas/Condition' description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. required: - type title: ToolMessageComplete ToolMessageFailedContentsItems: oneOf: - $ref: '#/components/schemas/TextContent' title: ToolMessageFailedContentsItems ToolMessageFailedType: type: string enum: - request-failed description: >- This message is triggered when the tool call fails. This message is never triggered for async tool calls. If this message is not provided, the model will be requested to respond. If this message is provided, only this message will be spoken and the model will not be requested to come up with a response. It's an exclusive OR. title: ToolMessageFailedType ToolMessageFailed: type: object properties: contents: type: array items: $ref: '#/components/schemas/ToolMessageFailedContentsItems' description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/ToolMessageFailedType' description: >- This message is triggered when the tool call fails. This message is never triggered for async tool calls. If this message is not provided, the model will be requested to respond. If this message is provided, only this message will be spoken and the model will not be requested to come up with a response. It's an exclusive OR. endCallAfterSpokenEnabled: type: boolean description: >- This is an optional boolean that if true, the call will end after the message is spoken. Default is false. @default false content: type: string description: >- This is the content that the assistant says when this message is triggered. conditions: type: array items: $ref: '#/components/schemas/Condition' description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. required: - type title: ToolMessageFailed ToolMessageDelayedContentsItems: oneOf: - $ref: '#/components/schemas/TextContent' title: ToolMessageDelayedContentsItems ToolMessageDelayedType: type: string enum: - request-response-delayed description: >- This message is triggered when the tool call is delayed. There are the two things that can trigger this message: 1. The user talks with the assistant while your server is processing the request. Default is "Sorry, a few more seconds." 2. The server doesn't respond within `timingMilliseconds`. This message is never triggered for async tool calls. title: ToolMessageDelayedType ToolMessageDelayed: type: object properties: contents: type: array items: $ref: '#/components/schemas/ToolMessageDelayedContentsItems' description: >- This is an alternative to the `content` property. It allows to specify variants of the same content, one per language. Usage: - If your assistants are multilingual, you can provide content for each language. - If you don't provide content for a language, the first item in the array will be automatically translated to the active language at that moment. This will override the `content` property. type: $ref: '#/components/schemas/ToolMessageDelayedType' description: >- This message is triggered when the tool call is delayed. There are the two things that can trigger this message: 1. The user talks with the assistant while your server is processing the request. Default is "Sorry, a few more seconds." 2. The server doesn't respond within `timingMilliseconds`. This message is never triggered for async tool calls. timingMilliseconds: type: number format: double description: >- The number of milliseconds to wait for the server response before saying this message. content: type: string description: >- This is the content that the assistant says when this message is triggered. conditions: type: array items: $ref: '#/components/schemas/Condition' description: >- This is an optional array of conditions that the tool call arguments must meet in order for this message to be triggered. required: - type title: ToolMessageDelayed ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingApiRequestMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingApiRequestMessagesItems ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingApiRequestMethod: type: string enum: - POST - GET - PUT - PATCH - DELETE title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingApiRequestMethod ToolParameterValue: oneOf: - type: string - type: number format: double - type: boolean - type: object additionalProperties: description: Any type - type: array items: description: Any type description: >- The value of the parameter. Any JSON type. String values support Liquid templates. title: ToolParameterValue ToolParameter: type: object properties: key: type: string description: This is the key of the parameter. value: $ref: '#/components/schemas/ToolParameterValue' description: >- The value of the parameter. Any JSON type. String values support Liquid templates. required: - key - value title: ToolParameter VariableExtractionAlias: type: object properties: key: type: string description: >- This is the key of the variable. This variable will be accessible during the call as `{{key}}` and stored in `call.artifact.variableValues` after the call. Rules: - Must start with a letter (a-z, A-Z). - Subsequent characters can be letters, numbers, or underscores. - Minimum length of 1 and maximum length of 40. value: type: string description: >- This is the value of the variable. This can reference existing variables, use filters, and perform transformations. Examples: "{{name}}", "{{customer.email}}", "Hello {{name | upcase}}" required: - key - value title: VariableExtractionAlias VariableExtractionPlan: type: object properties: schema: $ref: '#/components/schemas/JsonSchema' description: >- This is the schema to extract. Examples: 1. To extract object properties, you can use the following schema: ```json { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "number" } } } ``` These will be extracted as `{{ name }}` and `{{ age }}` respectively. To emphasize, object properties are extracted as direct global variables. 2. To extract nested properties, you can use the following schema: ```json { "type": "object", "properties": { "name": { "type": "object", "properties": { "first": { "type": "string" }, "last": { "type": "string" } } } } } ``` These will be extracted as `{{ name }}`. And, `{{ name.first }}` and `{{ name.last }}` will be accessible. 3. To extract array items, you can use the following schema: ```json { "type": "array", "title": "zipCodes", "items": { "type": "string" } } ``` This will be extracted as `{{ zipCodes }}`. To access the array items, you can use `{{ zipCodes[0] }}` and `{{ zipCodes[1] }}`. 4. To extract array of objects, you can use the following schema: ```json { "type": "array", "name": "people", "items": { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "number" }, "zipCodes": { "type": "array", "items": { "type": "string" } } } } } ``` This will be extracted as `{{ people }}`. To access the array items, you can use `{{ people[n].name }}`, `{{ people[n].age }}`, `{{ people[n].zipCodes }}`, `{{ people[n].zipCodes[0] }}` and `{{ people[n].zipCodes[1] }}`. aliases: type: array items: $ref: '#/components/schemas/VariableExtractionAlias' description: >- These are additional variables to create. These will be accessible during the call as `{{key}}` and stored in `call.artifact.variableValues` after the call. Example: ```json { "aliases": [ { "key": "customerName", "value": "{{name}}" }, { "key": "fullName", "value": "{{firstName}} {{lastName}}" }, { "key": "greeting", "value": "Hello {{name}}, welcome to {{company}}!" }, { "key": "customerCity", "value": "{{addresses[0].city}}" }, { "key": "something", "value": "{{any liquid}}" } ] } ``` This will create variables `customerName`, `fullName`, `greeting`, `customerCity`, and `something`. To access these variables, you can reference them as `{{customerName}}`, `{{fullName}}`, `{{greeting}}`, `{{customerCity}}`, and `{{something}}`. title: VariableExtractionPlan RegexConditionType: type: string enum: - regex description: This is the type discriminator for regex condition title: RegexConditionType MessageTargetRole: type: string enum: - user - assistant description: >- This is the role of the message to target. If not specified, will find the position in the message history ignoring role (effectively `any`). title: MessageTargetRole MessageTarget: type: object properties: role: $ref: '#/components/schemas/MessageTargetRole' description: >- This is the role of the message to target. If not specified, will find the position in the message history ignoring role (effectively `any`). position: type: number format: double description: >- This is the position of the message to target. - Negative numbers: Count from end (-1 = most recent, -2 = second most recent) - 0: First/oldest message in history - Positive numbers: Specific position (0-indexed from start) @default -1 (most recent message) title: MessageTarget RegexCondition: type: object properties: type: $ref: '#/components/schemas/RegexConditionType' description: This is the type discriminator for regex condition regex: type: string description: >- This is the regular expression pattern to match against message content. Note: - This works by using the RegExp.test method in Node.JS. Eg. /hello/.test("hello there") will return true. Hot tips: - In JavaScript, escape \ when sending the regex pattern. Eg. "hello\sthere" will be sent over the wire as "hellosthere". Send "hello\\sthere" instead. - RegExp.test does substring matching, so /cat/.test("I love cats") will return true. To do full string matching, use anchors: /^cat$/ will only match exactly "cat". - Word boundaries \b are useful for matching whole words: /\bcat\b/ matches "cat" but not "cats" or "category". - Use inline flags for portability: (?i) for case insensitive, (?m) for multiline target: $ref: '#/components/schemas/MessageTarget' description: >- This is the target for messages to check against. If not specified, the condition will run on the last message (position: -1). If role is not specified, it will look at the last message regardless of role. @default { position: -1 } negate: type: boolean description: >- This is the flag that when true, the condition matches if the pattern does NOT match. Useful for ensuring certain words/phrases are absent. @default false required: - type - regex title: RegexCondition LiquidConditionType: type: string enum: - liquid description: This is the type discriminator for liquid condition title: LiquidConditionType LiquidCondition: type: object properties: type: $ref: '#/components/schemas/LiquidConditionType' description: This is the type discriminator for liquid condition liquid: type: string description: >- This is the Liquid template that must return exactly "true" or "false" as a string. The template is evaluated and the entire output must be either "true" or "false" - nothing else. Available variables: - `messages`: Array of recent messages in OpenAI chat completions format (ChatCompletionMessageParam[]) Each message has properties like: role ('user', 'assistant', 'system'), content (string), etc. - `now`: Current timestamp in milliseconds (built-in Liquid variable) - Any assistant variable values (e.g., `userName`, `accountStatus`) Useful Liquid filters for messages: - `messages | last: 5` - Get the 5 most recent messages - `messages | where: 'role', 'user'` - Filter to only user messages - `messages | reverse` - Reverse the order of messages required: - type - liquid title: LiquidCondition GroupConditionType: type: string enum: - group description: This is the type discriminator for group condition title: GroupConditionType GroupConditionOperator: type: string enum: - AND - OR description: This is the logical operator for combining conditions in this group title: GroupConditionOperator GroupConditionConditionsItems: oneOf: - $ref: '#/components/schemas/RegexCondition' - $ref: '#/components/schemas/LiquidCondition' - $ref: '#/components/schemas/GroupCondition' title: GroupConditionConditionsItems GroupCondition: type: object properties: type: $ref: '#/components/schemas/GroupConditionType' description: This is the type discriminator for group condition operator: $ref: '#/components/schemas/GroupConditionOperator' description: This is the logical operator for combining conditions in this group conditions: type: array items: $ref: '#/components/schemas/GroupConditionConditionsItems' description: |- This is the list of nested conditions to evaluate. Supports recursive nesting of groups for complex logic. required: - type - operator - conditions title: GroupCondition ToolRejectionPlanConditionsItems: oneOf: - $ref: '#/components/schemas/RegexCondition' - $ref: '#/components/schemas/LiquidCondition' - $ref: '#/components/schemas/GroupCondition' title: ToolRejectionPlanConditionsItems ToolRejectionPlan: type: object properties: conditions: type: array items: $ref: '#/components/schemas/ToolRejectionPlanConditionsItems' description: >- This is the list of conditions that must be evaluated. Usage: - If all conditions match (AND logic), the tool call is rejected. - For OR logic at the top level, use a single 'group' condition with operator: 'OR'. @default [] - Empty array means tool always executes title: ToolRejectionPlan CreateApiRequestToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingApiRequestMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. method: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingApiRequestMethod timeoutSeconds: type: number format: double description: >- This is the timeout in seconds for the request. Defaults to 20 seconds. @default 20 credentialId: type: string description: The credential ID for API request authentication encryptedPaths: type: array items: type: string description: >- This is the paths to encrypt in the request body if credentialId and encryptionPlan are defined. parameters: type: array items: $ref: '#/components/schemas/ToolParameter' description: >- Static key-value pairs merged into the request body. Values support Liquid templates. name: type: string description: >- This is the name of the tool. This will be passed to the model. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 40. description: type: string description: >- This is the description of the tool. This will be passed to the model. url: type: string description: This is where the request will be sent. body: $ref: '#/components/schemas/JsonSchema' description: This is the body of the request. headers: $ref: '#/components/schemas/JsonSchema' description: These are the headers to send with the request. backoffPlan: $ref: '#/components/schemas/BackoffPlan' description: >- This is the backoff plan if the request fails. Defaults to undefined (the request will not be retried). @default undefined (the request will not be retried) variableExtractionPlan: $ref: '#/components/schemas/VariableExtractionPlan' description: >- This is the plan to extract variables from the tool's response. These will be accessible during the call and stored in `call.artifact.variableValues` after the call. Usage: 1. Use `aliases` to extract variables from the tool's response body. (Most common case) ```json { "aliases": [ { "key": "customerName", "value": "{{customer.name}}" }, { "key": "customerAge", "value": "{{customer.age}}" } ] } ``` The tool response body is made available to the liquid template. 2. Use `aliases` to extract variables from the tool's response body if the response is an array. ```json { "aliases": [ { "key": "customerName", "value": "{{$[0].name}}" }, { "key": "customerAge", "value": "{{$[0].age}}" } ] } ``` $ is a shorthand for the tool's response body. `$[0]` is the first item in the array. `$[n]` is the nth item in the array. Note, $ is available regardless of the response body type (both object and array). 3. Use `aliases` to extract variables from the tool's response headers. ```json { "aliases": [ { "key": "customerName", "value": "{{tool.response.headers.customer-name}}" }, { "key": "customerAge", "value": "{{tool.response.headers.customer-age}}" } ] } ``` `tool.response` is made available to the liquid template. Particularly, both `tool.response.headers` and `tool.response.body` are available. Note, `tool.response` is available regardless of the response body type (both object and array). 4. Use `schema` to extract a large portion of the tool's response body. 4.1. If you hit example.com and it returns `{"name": "John", "age": 30}`, then you can specify the schema as: ```json { "schema": { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "number" } } } } ``` These will be extracted as `{{ name }}` and `{{ age }}` respectively. To emphasize, object properties are extracted as direct global variables. 4.2. If you hit example.com and it returns `{"name": {"first": "John", "last": "Doe"}}`, then you can specify the schema as: ```json { "schema": { "type": "object", "properties": { "name": { "type": "object", "properties": { "first": { "type": "string" }, "last": { "type": "string" } } } } } } ``` These will be extracted as `{{ name }}`. And, `{{ name.first }}` and `{{ name.last }}` will be accessible. 4.3. If you hit example.com and it returns `["94123", "94124"]`, then you can specify the schema as: ```json { "schema": { "type": "array", "title": "zipCodes", "items": { "type": "string" } } } ``` This will be extracted as `{{ zipCodes }}`. To access the array items, you can use `{{ zipCodes[0] }}` and `{{ zipCodes[1] }}`. 4.4. If you hit example.com and it returns `[{"name": "John", "age": 30, "zipCodes": ["94123", "94124"]}, {"name": "Jane", "age": 25, "zipCodes": ["94125", "94126"]}]`, then you can specify the schema as: ```json { "schema": { "type": "array", "title": "people", "items": { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "number" }, "zipCodes": { "type": "array", "items": { "type": "string" } } } } } } ``` This will be extracted as `{{ people }}`. To access the array items, you can use `{{ people[n].name }}`, `{{ people[n].age }}`, `{{ people[n].zipCodes }}`, `{{ people[n].zipCodes[0] }}` and `{{ people[n].zipCodes[1] }}`. Note: Both `aliases` and `schema` can be used together. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` required: - method - url title: CreateApiRequestToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingBashMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingBashMessagesItems ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingBashSubType: type: string enum: - bash_20241022 description: The sub type of tool. title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingBashSubType ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingBashName: type: string enum: - bash default: bash description: The name of the tool, fixed to 'bash' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingBashName CreateBashToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingBashMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. subType: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingBashSubType description: The sub type of tool. server: $ref: '#/components/schemas/Server' description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. name: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingBashName description: The name of the tool, fixed to 'bash' rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` required: - subType - name title: CreateBashToolDTO CreateCodeToolDtoMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: CreateCodeToolDtoMessagesItems CreateCodeToolDtoType: type: string enum: - code description: The type of tool. "code" for Code tool. title: CreateCodeToolDtoType CodeToolEnvironmentVariable: type: object properties: name: type: string description: Name of the environment variable value: type: string description: Value of the environment variable. Supports Liquid templates. required: - name - value title: CodeToolEnvironmentVariable OpenAiFunctionParametersType: type: string enum: - object description: >- This must be set to 'object'. It instructs the model to return a JSON object containing the function call properties. title: OpenAiFunctionParametersType OpenAIFunctionParameters: type: object properties: type: $ref: '#/components/schemas/OpenAiFunctionParametersType' description: >- This must be set to 'object'. It instructs the model to return a JSON object containing the function call properties. properties: type: object additionalProperties: $ref: '#/components/schemas/JsonSchema' description: >- This provides a description of the properties required by the function. JSON Schema can be used to specify expectations for each property. Refer to [this doc](https://ajv.js.org/json-schema.html#json-data-type) for a comprehensive guide on JSON Schema. required: type: array items: type: string description: This specifies the properties that are required by the function. required: - type - properties title: OpenAIFunctionParameters OpenAIFunction: type: object properties: strict: type: boolean default: false description: >- This is a boolean that controls whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the [OpenAI guide](https://openai.com/index/introducing-structured-outputs-in-the-api/). @default false name: type: string description: >- This is the the name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. description: type: string description: >- This is the description of what the function does, used by the AI to choose when and how to call the function. parameters: $ref: '#/components/schemas/OpenAIFunctionParameters' description: >- These are the parameters the functions accepts, described as a JSON Schema object. See the [OpenAI guide](https://platform.openai.com/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema) for documentation about the format. Omitting parameters defines a function with an empty parameter list. required: - name title: OpenAIFunction CreateCodeToolDTO: type: object properties: messages: type: array items: $ref: '#/components/schemas/CreateCodeToolDtoMessagesItems' description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. type: $ref: '#/components/schemas/CreateCodeToolDtoType' description: The type of tool. "code" for Code tool. async: type: boolean description: |- This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (`false`). server: $ref: '#/components/schemas/Server' description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. code: type: string description: TypeScript code to execute when the tool is called environmentVariables: type: array items: $ref: '#/components/schemas/CodeToolEnvironmentVariable' description: Environment variables available in code via `env` object timeoutSeconds: type: number format: double description: >- This is the timeout in seconds for the code execution. Defaults to 10 seconds. Maximum is 30 seconds to prevent abuse. @default 10 credentialId: type: string description: Credential ID containing the Val Town API key variableExtractionPlan: $ref: '#/components/schemas/VariableExtractionPlan' description: Plan to extract variables from the tool response function: $ref: '#/components/schemas/OpenAIFunction' description: >- This is the function definition of the tool. For the Code tool, this defines the name, description, and parameters that the model will use to understand when and how to call this tool. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` required: - type - code title: CreateCodeToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingComputerMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingComputerMessagesItems ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingComputerSubType: type: string enum: - computer_20241022 description: The sub type of tool. title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingComputerSubType ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingComputerName: type: string enum: - computer default: computer description: The name of the tool, fixed to 'computer' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingComputerName CreateComputerToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingComputerMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. subType: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingComputerSubType description: The sub type of tool. server: $ref: '#/components/schemas/Server' description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. name: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingComputerName description: The name of the tool, fixed to 'computer' displayWidthPx: type: number format: double description: The display width in pixels displayHeightPx: type: number format: double description: The display height in pixels displayNumber: type: number format: double description: Optional display number rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` required: - subType - name - displayWidthPx - displayHeightPx title: CreateComputerToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingDtmfMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingDtmfMessagesItems CreateDtmfToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingDtmfMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. sipInfoDtmfEnabled: type: boolean default: false description: >- This enables sending DTMF tones via SIP INFO messages instead of RFC 2833 (RTP events). When enabled, DTMF digits will be sent using the SIP INFO method, which can be more reliable in some network configurations. Only relevant when using the `vapi.sip` transport. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateDtmfToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingEndCallMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingEndCallMessagesItems CreateEndCallToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingEndCallMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateEndCallToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingFunctionMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingFunctionMessagesItems CreateFunctionToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingFunctionMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. async: type: boolean description: |- This determines if the tool is async. If async, the assistant will move forward without waiting for your server to respond. This is useful if you just want to trigger something on your server. If sync, the assistant will wait for your server to respond. This is useful if want assistant to respond with the result from your server. Defaults to synchronous (`false`). server: $ref: '#/components/schemas/Server' description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. variableExtractionPlan: $ref: '#/components/schemas/VariableExtractionPlan' description: Plan to extract variables from the tool response parameters: type: array items: $ref: '#/components/schemas/ToolParameter' description: >- Static key-value pairs merged into the request body. Values support Liquid templates. function: $ref: '#/components/schemas/OpenAIFunction' description: This is the function definition of the tool. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateFunctionToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelCalendarAvailabilityCheckMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelCalendarAvailabilityCheckMessagesItems CreateGoHighLevelCalendarAvailabilityToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelCalendarAvailabilityCheckMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateGoHighLevelCalendarAvailabilityToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelCalendarEventCreateMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelCalendarEventCreateMessagesItems CreateGoHighLevelCalendarEventCreateToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelCalendarEventCreateMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateGoHighLevelCalendarEventCreateToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelContactCreateMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelContactCreateMessagesItems CreateGoHighLevelContactCreateToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelContactCreateMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateGoHighLevelContactCreateToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelContactGetMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelContactGetMessagesItems CreateGoHighLevelContactGetToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGohighlevelContactGetMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateGoHighLevelContactGetToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGoogleCalendarAvailabilityCheckMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGoogleCalendarAvailabilityCheckMessagesItems CreateGoogleCalendarCheckAvailabilityToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGoogleCalendarAvailabilityCheckMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateGoogleCalendarCheckAvailabilityToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGoogleCalendarEventCreateMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGoogleCalendarEventCreateMessagesItems CreateGoogleCalendarCreateEventToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGoogleCalendarEventCreateMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateGoogleCalendarCreateEventToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGoogleSheetsRowAppendMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGoogleSheetsRowAppendMessagesItems CreateGoogleSheetsRowAppendToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingGoogleSheetsRowAppendMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateGoogleSheetsRowAppendToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingHandoffMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingHandoffMessagesItems HandoffDestinationAssistantType: type: string enum: - assistant title: HandoffDestinationAssistantType ContextEngineeringPlanUserAndAssistantMessagesType: type: string enum: - userAndAssistantMessages title: ContextEngineeringPlanUserAndAssistantMessagesType ContextEngineeringPlanUserAndAssistantMessages: type: object properties: type: $ref: >- #/components/schemas/ContextEngineeringPlanUserAndAssistantMessagesType required: - type title: ContextEngineeringPlanUserAndAssistantMessages HandoffDestinationAssistantContextEngineeringPlan: oneOf: - $ref: '#/components/schemas/ContextEngineeringPlanLastNMessages' - $ref: '#/components/schemas/ContextEngineeringPlanNone' - $ref: '#/components/schemas/ContextEngineeringPlanAll' - $ref: '#/components/schemas/ContextEngineeringPlanUserAndAssistantMessages' description: >- This is the plan for manipulating the message context before handing off the call to the next assistant. title: HandoffDestinationAssistantContextEngineeringPlan AssistantOverridesTranscriber: oneOf: - $ref: '#/components/schemas/AssemblyAITranscriber' - $ref: '#/components/schemas/AzureSpeechTranscriber' - $ref: '#/components/schemas/CustomTranscriber' - $ref: '#/components/schemas/DeepgramTranscriber' - $ref: '#/components/schemas/ElevenLabsTranscriber' - $ref: '#/components/schemas/GladiaTranscriber' - $ref: '#/components/schemas/GoogleTranscriber' - $ref: '#/components/schemas/SpeechmaticsTranscriber' - $ref: '#/components/schemas/TalkscriberTranscriber' - $ref: '#/components/schemas/OpenAITranscriber' - $ref: '#/components/schemas/CartesiaTranscriber' - $ref: '#/components/schemas/SonioxTranscriber' description: These are the options for the assistant's transcriber. title: AssistantOverridesTranscriber ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingMcpMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingMcpMessagesItems McpToolMessagesMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: McpToolMessagesMessagesItems McpToolMessages: type: object properties: name: type: string description: The name of the tool from the MCP server. messages: type: array items: $ref: '#/components/schemas/McpToolMessagesMessagesItems' description: >- Custom messages for this specific tool. Set to an empty array to suppress all messages for this tool. If not provided, the tool will use the default messages from the parent MCP tool configuration. required: - name title: McpToolMessages McpToolMetadataProtocol: type: string enum: - sse - shttp description: >- This is the protocol used for MCP communication. Defaults to Streamable HTTP. title: McpToolMetadataProtocol McpToolMetadata: type: object properties: protocol: $ref: '#/components/schemas/McpToolMetadataProtocol' description: >- This is the protocol used for MCP communication. Defaults to Streamable HTTP. title: McpToolMetadata CreateMcpToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingMcpMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. server: $ref: '#/components/schemas/Server' description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. toolMessages: type: array items: $ref: '#/components/schemas/McpToolMessages' description: >- Per-tool message overrides for individual tools loaded from the MCP server. Set messages to an empty array to suppress messages for a specific tool. Tools not listed here will use the default messages from the parent tool. metadata: $ref: '#/components/schemas/McpToolMetadata' rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateMcpToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingQueryMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingQueryMessagesItems KnowledgeBaseProvider: type: string enum: - google description: The provider of the knowledge base title: KnowledgeBaseProvider KnowledgeBaseModel: type: string enum: - gemini-3-flash-preview - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.0-flash-thinking-exp - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.0-flash-exp - gemini-2.0-flash-realtime-exp - gemini-1.5-flash - gemini-1.5-flash-002 - gemini-1.5-pro - gemini-1.5-pro-002 - gemini-1.0-pro description: The model to use for the knowledge base title: KnowledgeBaseModel KnowledgeBase: type: object properties: name: type: string description: The name of the knowledge base provider: $ref: '#/components/schemas/KnowledgeBaseProvider' description: The provider of the knowledge base model: $ref: '#/components/schemas/KnowledgeBaseModel' description: The model to use for the knowledge base description: type: string description: A description of the knowledge base fileIds: type: array items: type: string description: The file IDs associated with this knowledge base required: - name - provider - description - fileIds title: KnowledgeBase CreateQueryToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingQueryMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. knowledgeBases: type: array items: $ref: '#/components/schemas/KnowledgeBase' description: The knowledge bases to query rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateQueryToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSlackMessageSendMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSlackMessageSendMessagesItems CreateSlackSendMessageToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSlackMessageSendMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateSlackSendMessageToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSmsMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSmsMessagesItems CreateSmsToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSmsMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateSmsToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTextEditorMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTextEditorMessagesItems ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTextEditorSubType: type: string enum: - text_editor_20241022 description: The sub type of tool. title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTextEditorSubType ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTextEditorName: type: string enum: - str_replace_editor default: str_replace_editor description: The name of the tool, fixed to 'str_replace_editor' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTextEditorName CreateTextEditorToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTextEditorMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. subType: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTextEditorSubType description: The sub type of tool. server: $ref: '#/components/schemas/Server' description: |2- This is the server where a `tool-calls` webhook will be sent. Notes: - Webhook is sent to this server when a tool call is made. - Webhook contains the call, assistant, and phone number objects. - Webhook contains the variables set on the assistant. - Webhook is sent to the first available URL in this order: {{tool.server.url}}, {{assistant.server.url}}, {{phoneNumber.server.url}}, {{org.server.url}}. - Webhook expects a response with tool call result. name: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTextEditorName description: The name of the tool, fixed to 'str_replace_editor' rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` required: - subType - name title: CreateTextEditorToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTransferCallMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTransferCallMessagesItems TransferDestinationAssistantMessage: oneOf: - type: string - $ref: '#/components/schemas/CustomMessage' description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. title: TransferDestinationAssistantMessage TransferDestinationAssistantType: type: string enum: - assistant title: TransferDestinationAssistantType TransferMode: type: string enum: - rolling-history - swap-system-message-in-history title: TransferMode TransferDestinationAssistant: type: object properties: message: $ref: '#/components/schemas/TransferDestinationAssistantMessage' description: >- This is spoken to the customer before connecting them to the destination. Usage: - If this is not provided and transfer tool messages is not provided, default is "Transferring the call now". - If set to "", nothing is spoken. This is useful when you want to silently transfer. This is especially useful when transferring between assistants in a squad. In this scenario, you likely also want to set `assistant.firstMessageMode=assistant-speaks-first-with-model-generated-message` for the destination assistant. This accepts a string or a ToolMessageStart class. Latter is useful if you want to specify multiple messages for different languages through the `contents` field. type: $ref: '#/components/schemas/TransferDestinationAssistantType' transferMode: $ref: '#/components/schemas/TransferMode' description: >- This is the mode to use for the transfer. Defaults to `rolling-history`. - `rolling-history`: This is the default mode. It keeps the entire conversation history and appends the new assistant's system message on transfer. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) Post-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) system: assistant2 system message assistant: assistant2 first message (or model generated if firstMessageMode is set to `assistant-speaks-first-with-model-generated-message`) - `swap-system-message-in-history`: This replaces the original system message with the new assistant's system message on transfer. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) Post-transfer: system: assistant2 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) assistant: assistant2 first message (or model generated if firstMessageMode is set to `assistant-speaks-first-with-model-generated-message`) - `delete-history`: This deletes the entire conversation history on transfer. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) Post-transfer: system: assistant2 system message assistant: assistant2 first message user: Yes, please assistant: how can i help? user: i need help with my account - `swap-system-message-in-history-and-remove-transfer-tool-messages`: This replaces the original system message with the new assistant's system message on transfer and removes transfer tool messages from conversation history sent to the LLM. Example: Pre-transfer: system: assistant1 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account transfer-tool transfer-tool-result assistant: (destination.message) Post-transfer: system: assistant2 system message assistant: assistant1 first message user: hey, good morning assistant: how can i help? user: i need help with my account assistant: (destination.message) assistant: assistant2 first message (or model generated if firstMessageMode is set to `assistant-speaks-first-with-model-generated-message`) @default 'rolling-history' assistantName: type: string description: This is the assistant to transfer the call to. description: type: string description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. required: - type - assistantName title: TransferDestinationAssistant ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTransferCallDestinationsItems: oneOf: - $ref: '#/components/schemas/TransferDestinationAssistant' - $ref: '#/components/schemas/TransferDestinationNumber' - $ref: '#/components/schemas/TransferDestinationSip' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTransferCallDestinationsItems CreateTransferCallToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTransferCallMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. destinations: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingTransferCallDestinationsItems description: >- These are the destinations that the call can be transferred to. If no destinations are provided, server.url will be used to get the transfer destination once the tool is called. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateTransferCallToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSipRequestMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSipRequestMessagesItems ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSipRequestVerb: type: string enum: - INFO - MESSAGE - NOTIFY description: The SIP method to send. title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSipRequestVerb ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSipRequestBody: oneOf: - type: string - $ref: '#/components/schemas/JsonSchema' description: >- Body to include in the SIP request. Either a literal string body, or a JSON schema describing a structured body that the model should populate. title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSipRequestBody CreateSipRequestToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSipRequestMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. verb: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSipRequestVerb description: The SIP method to send. headers: $ref: '#/components/schemas/JsonSchema' description: >- JSON schema for headers the model should populate when sending the SIP request. body: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingSipRequestBody description: >- Body to include in the SIP request. Either a literal string body, or a JSON schema describing a structured body that the model should populate. rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` required: - verb title: CreateSipRequestToolDTO ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingVoicemailMessagesItems: oneOf: - $ref: '#/components/schemas/ToolMessageStart' - $ref: '#/components/schemas/ToolMessageComplete' - $ref: '#/components/schemas/ToolMessageFailed' - $ref: '#/components/schemas/ToolMessageDelayed' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingVoicemailMessagesItems CreateVoicemailToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingVoicemailMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. beepDetectionEnabled: type: boolean default: false description: >- This is the flag that enables beep detection for voicemail detection and applies only for twilio based calls. @default false rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateVoicemailToolDTO AnthropicBedrockModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: AnthropicBedrockModelToolsItems CreateCustomKnowledgeBaseDtoProvider: type: string enum: - custom-knowledge-base description: This knowledge base is bring your own knowledge base implementation. title: CreateCustomKnowledgeBaseDtoProvider CreateCustomKnowledgeBaseDTO: type: object properties: provider: $ref: '#/components/schemas/CreateCustomKnowledgeBaseDtoProvider' description: This knowledge base is bring your own knowledge base implementation. server: $ref: '#/components/schemas/Server' description: |- This is where the knowledge base request will be sent. Request Example: POST https://{server.url} Content-Type: application/json { "messsage": { "type": "knowledge-base-request", "messages": [ { "role": "user", "content": "Why is ocean blue?" } ], ...other metadata about the call... } } Response Expected: ``` { "message": { "role": "assistant", "content": "The ocean is blue because water absorbs everything but blue.", }, // YOU CAN RETURN THE EXACT RESPONSE TO SPEAK "documents": [ { "content": "The ocean is blue primarily because water absorbs colors in the red part of the light spectrum and scatters the blue light, making it more visible to our eyes.", "similarity": 1 }, { "content": "Blue light is scattered more by the water molecules than other colors, enhancing the blue appearance of the ocean.", "similarity": .5 } ] // OR, YOU CAN RETURN AN ARRAY OF DOCUMENTS THAT WILL BE SENT TO THE MODEL } ``` required: - provider - server title: CreateCustomKnowledgeBaseDTO AnthropicBedrockModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: AnthropicBedrockModelKnowledgeBase AnthropicBedrockModelProvider: type: string enum: - anthropic-bedrock description: The provider identifier for Anthropic via AWS Bedrock. title: AnthropicBedrockModelProvider AnthropicBedrockModelModel: type: string enum: - claude-3-opus-20240229 - claude-3-sonnet-20240229 - claude-3-haiku-20240307 - claude-3-5-sonnet-20240620 - claude-3-5-sonnet-20241022 - claude-3-5-haiku-20241022 - claude-3-7-sonnet-20250219 - claude-opus-4-20250514 - claude-opus-4-5-20251101 - claude-opus-4-6 - claude-sonnet-4-20250514 - claude-sonnet-4-5-20250929 - claude-sonnet-4-6 - claude-haiku-4-5-20251001 description: The specific Anthropic/Claude model that will be used via Bedrock. title: AnthropicBedrockModelModel AnthropicBedrockModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/AnthropicBedrockModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/AnthropicBedrockModelKnowledgeBase' description: These are the options for the knowledge base. provider: $ref: '#/components/schemas/AnthropicBedrockModelProvider' description: The provider identifier for Anthropic via AWS Bedrock. model: $ref: '#/components/schemas/AnthropicBedrockModelModel' description: The specific Anthropic/Claude model that will be used via Bedrock. thinking: $ref: '#/components/schemas/AnthropicThinkingConfig' description: |- Optional configuration for Anthropic's thinking feature. Only applicable for claude-3-7-sonnet-20250219 model. If provided, maxTokens must be greater than thinking.budgetTokens. temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - provider - model title: AnthropicBedrockModel AnyscaleModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: AnyscaleModelToolsItems AnyscaleModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: AnyscaleModelKnowledgeBase AnyscaleModelProvider: type: string enum: - anyscale title: AnyscaleModelProvider AnyscaleModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/AnyscaleModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/AnyscaleModelKnowledgeBase' description: These are the options for the knowledge base. provider: $ref: '#/components/schemas/AnyscaleModelProvider' model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - provider - model title: AnyscaleModel CerebrasModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: CerebrasModelToolsItems CerebrasModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: CerebrasModelKnowledgeBase CerebrasModelModel: type: string enum: - llama3.1-8b - llama-3.3-70b description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b title: CerebrasModelModel CerebrasModelProvider: type: string enum: - cerebras title: CerebrasModelProvider CerebrasModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/CerebrasModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/CerebrasModelKnowledgeBase' description: These are the options for the knowledge base. model: $ref: '#/components/schemas/CerebrasModelModel' description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b provider: $ref: '#/components/schemas/CerebrasModelProvider' temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - model - provider title: CerebrasModel CustomLlmModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: CustomLlmModelToolsItems CustomLlmModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: CustomLlmModelKnowledgeBase CustomLlmModelProvider: type: string enum: - custom-llm description: >- This is the provider that will be used for the model. Any service, including your own server, that is compatible with the OpenAI API can be used. title: CustomLlmModelProvider CustomLlmModelMetadataSendMode: type: string enum: - 'off' - variable - destructured description: >- This determines whether metadata is sent in requests to the custom provider. - `off` will not send any metadata. payload will look like `{ messages }` - `variable` will send `assistant.metadata` as a variable on the payload. payload will look like `{ messages, metadata }` - `destructured` will send `assistant.metadata` fields directly on the payload. payload will look like `{ messages, ...metadata }` Further, `variable` and `destructured` will send `call`, `phoneNumber`, and `customer` objects in the payload. Default is `variable`. title: CustomLlmModelMetadataSendMode CustomLLMModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/CustomLlmModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/CustomLlmModelKnowledgeBase' description: These are the options for the knowledge base. provider: $ref: '#/components/schemas/CustomLlmModelProvider' description: >- This is the provider that will be used for the model. Any service, including your own server, that is compatible with the OpenAI API can be used. metadataSendMode: $ref: '#/components/schemas/CustomLlmModelMetadataSendMode' description: >- This determines whether metadata is sent in requests to the custom provider. - `off` will not send any metadata. payload will look like `{ messages }` - `variable` will send `assistant.metadata` as a variable on the payload. payload will look like `{ messages, metadata }` - `destructured` will send `assistant.metadata` fields directly on the payload. payload will look like `{ messages, ...metadata }` Further, `variable` and `destructured` will send `call`, `phoneNumber`, and `customer` objects in the payload. Default is `variable`. headers: type: object additionalProperties: type: string description: >- Custom headers to send with requests. These headers can override default OpenAI headers except for Authorization (which should be specified using a custom-llm credential). url: type: string description: >- These is the URL we'll use for the OpenAI client's `baseURL`. Ex. https://openrouter.ai/api/v1 wordLevelConfidenceEnabled: type: boolean description: >- This determines whether the transcriber's word level confidence is sent in requests to the custom provider. Default is false. This only works for Deepgram transcribers. timeoutSeconds: type: number format: double description: >- This sets the timeout for the connection to the custom provider without needing to stream any tokens back. Default is 20 seconds. model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - provider - url - model title: CustomLLMModel DeepInfraModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: DeepInfraModelToolsItems DeepInfraModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: DeepInfraModelKnowledgeBase DeepInfraModelProvider: type: string enum: - deepinfra title: DeepInfraModelProvider DeepInfraModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/DeepInfraModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/DeepInfraModelKnowledgeBase' description: These are the options for the knowledge base. provider: $ref: '#/components/schemas/DeepInfraModelProvider' model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - provider - model title: DeepInfraModel DeepSeekModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: DeepSeekModelToolsItems DeepSeekModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: DeepSeekModelKnowledgeBase DeepSeekModelModel: type: string enum: - deepseek-chat - deepseek-reasoner description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b title: DeepSeekModelModel DeepSeekModelProvider: type: string enum: - deep-seek title: DeepSeekModelProvider DeepSeekModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/DeepSeekModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/DeepSeekModelKnowledgeBase' description: These are the options for the knowledge base. model: $ref: '#/components/schemas/DeepSeekModelModel' description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b provider: $ref: '#/components/schemas/DeepSeekModelProvider' temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - model - provider title: DeepSeekModel GoogleModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: GoogleModelToolsItems GoogleModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: GoogleModelKnowledgeBase GoogleModelModel: type: string enum: - gemini-3-flash-preview - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-2.0-flash-thinking-exp - gemini-2.0-pro-exp-02-05 - gemini-2.0-flash - gemini-2.0-flash-lite - gemini-2.0-flash-exp - gemini-2.0-flash-realtime-exp - gemini-1.5-flash - gemini-1.5-flash-002 - gemini-1.5-pro - gemini-1.5-pro-002 - gemini-1.0-pro description: This is the Google model that will be used. title: GoogleModelModel GoogleModelProvider: type: string enum: - google title: GoogleModelProvider GeminiMultimodalLivePrebuiltVoiceConfigVoiceName: type: string enum: - Puck - Charon - Kore - Fenrir - Aoede title: GeminiMultimodalLivePrebuiltVoiceConfigVoiceName GeminiMultimodalLivePrebuiltVoiceConfig: type: object properties: voiceName: $ref: >- #/components/schemas/GeminiMultimodalLivePrebuiltVoiceConfigVoiceName required: - voiceName title: GeminiMultimodalLivePrebuiltVoiceConfig GeminiMultimodalLiveVoiceConfig: type: object properties: prebuiltVoiceConfig: $ref: '#/components/schemas/GeminiMultimodalLivePrebuiltVoiceConfig' required: - prebuiltVoiceConfig title: GeminiMultimodalLiveVoiceConfig GeminiMultimodalLiveSpeechConfig: type: object properties: voiceConfig: $ref: '#/components/schemas/GeminiMultimodalLiveVoiceConfig' required: - voiceConfig title: GeminiMultimodalLiveSpeechConfig GoogleRealtimeConfig: type: object properties: topP: type: number format: double description: >- This is the nucleus sampling parameter that controls the cumulative probability of tokens considered during text generation. Only applicable with the Gemini Flash 2.0 Multimodal Live API. topK: type: number format: double description: >- This is the top-k sampling parameter that limits the number of highest probability tokens considered during text generation. Only applicable with the Gemini Flash 2.0 Multimodal Live API. presencePenalty: type: number format: double description: >- This is the presence penalty parameter that influences the model's likelihood to repeat information by penalizing tokens based on their presence in the text. Only applicable with the Gemini Flash 2.0 Multimodal Live API. frequencyPenalty: type: number format: double description: >- This is the frequency penalty parameter that influences the model's likelihood to repeat tokens by penalizing them based on their frequency in the text. Only applicable with the Gemini Flash 2.0 Multimodal Live API. speechConfig: $ref: '#/components/schemas/GeminiMultimodalLiveSpeechConfig' description: >- This is the speech configuration object that defines the voice settings to be used for the model's speech output. Only applicable with the Gemini Flash 2.0 Multimodal Live API. title: GoogleRealtimeConfig GoogleModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/GoogleModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/GoogleModelKnowledgeBase' description: These are the options for the knowledge base. model: $ref: '#/components/schemas/GoogleModelModel' description: This is the Google model that will be used. provider: $ref: '#/components/schemas/GoogleModelProvider' realtimeConfig: $ref: '#/components/schemas/GoogleRealtimeConfig' description: >- This is the session configuration for the Gemini Flash 2.0 Multimodal Live API. Only applicable if the model `gemini-2.0-flash-realtime-exp` is selected. temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - model - provider title: GoogleModel GroqModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: GroqModelToolsItems GroqModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: GroqModelKnowledgeBase GroqModelModel: type: string enum: - openai/gpt-oss-20b - openai/gpt-oss-120b - deepseek-r1-distill-llama-70b - llama-3.3-70b-versatile - llama-3.1-405b-reasoning - llama-3.1-8b-instant - llama3-8b-8192 - llama3-70b-8192 - gemma2-9b-it - moonshotai/kimi-k2-instruct-0905 - meta-llama/llama-4-maverick-17b-128e-instruct - meta-llama/llama-4-scout-17b-16e-instruct - mistral-saba-24b - compound-beta - compound-beta-mini description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b title: GroqModelModel GroqModelProvider: type: string enum: - groq title: GroqModelProvider GroqModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/GroqModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/GroqModelKnowledgeBase' description: These are the options for the knowledge base. model: $ref: '#/components/schemas/GroqModelModel' description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b provider: $ref: '#/components/schemas/GroqModelProvider' temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - model - provider title: GroqModel InflectionAiModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: InflectionAiModelToolsItems InflectionAiModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: InflectionAiModelKnowledgeBase InflectionAiModelModel: type: string enum: - inflection_3_pi description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b title: InflectionAiModelModel InflectionAiModelProvider: type: string enum: - inflection-ai title: InflectionAiModelProvider InflectionAIModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/InflectionAiModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/InflectionAiModelKnowledgeBase' description: These are the options for the knowledge base. model: $ref: '#/components/schemas/InflectionAiModelModel' description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b provider: $ref: '#/components/schemas/InflectionAiModelProvider' temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - model - provider title: InflectionAIModel MinimaxLlmModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: MinimaxLlmModelToolsItems MinimaxLlmModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: MinimaxLlmModelKnowledgeBase MinimaxLlmModelProvider: type: string enum: - minimax title: MinimaxLlmModelProvider MinimaxLlmModelModel: type: string enum: - MiniMax-M2.7 description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b title: MinimaxLlmModelModel MinimaxLLMModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/MinimaxLlmModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/MinimaxLlmModelKnowledgeBase' description: These are the options for the knowledge base. provider: $ref: '#/components/schemas/MinimaxLlmModelProvider' model: $ref: '#/components/schemas/MinimaxLlmModelModel' description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - provider - model title: MinimaxLLMModel OpenAiModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: OpenAiModelToolsItems OpenAiModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: OpenAiModelKnowledgeBase OpenAiModelProvider: type: string enum: - openai description: This is the provider that will be used for the model. title: OpenAiModelProvider OpenAiModelModel: type: string enum: - gpt-5.4 - gpt-5.4-mini - gpt-5.4-nano - gpt-5.2 - gpt-5.2-chat-latest - gpt-5.1 - gpt-5.1-chat-latest - gpt-5 - gpt-5-chat-latest - gpt-5-mini - gpt-5-nano - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - chatgpt-4o-latest - o3 - o3-mini - o4-mini - o1-mini - o1-mini-2024-09-12 - gpt-4o-realtime-preview-2024-10-01 - gpt-4o-realtime-preview-2024-12-17 - gpt-4o-mini-realtime-preview-2024-12-17 - gpt-realtime-2025-08-28 - gpt-realtime-mini-2025-12-15 - gpt-4o-mini-2024-07-18 - gpt-4o-mini - gpt-4o - gpt-4o-2024-05-13 - gpt-4o-2024-08-06 - gpt-4o-2024-11-20 - gpt-4-turbo - gpt-4-turbo-2024-04-09 - gpt-4-turbo-preview - gpt-4-0125-preview - gpt-4-1106-preview - gpt-4 - gpt-4-0613 - gpt-3.5-turbo - gpt-3.5-turbo-0125 - gpt-3.5-turbo-1106 - gpt-3.5-turbo-16k - gpt-3.5-turbo-0613 - gpt-4.1-2025-04-14:westus - gpt-4.1-2025-04-14:eastus2 - gpt-4.1-2025-04-14:eastus - gpt-4.1-2025-04-14:westus3 - gpt-4.1-2025-04-14:northcentralus - gpt-4.1-2025-04-14:southcentralus - gpt-4.1-2025-04-14:westeurope - gpt-4.1-2025-04-14:germanywestcentral - gpt-4.1-2025-04-14:polandcentral - gpt-4.1-2025-04-14:spaincentral - gpt-4.1-mini-2025-04-14:westus - gpt-4.1-mini-2025-04-14:eastus2 - gpt-4.1-mini-2025-04-14:eastus - gpt-4.1-mini-2025-04-14:westus3 - gpt-4.1-mini-2025-04-14:northcentralus - gpt-4.1-mini-2025-04-14:southcentralus - gpt-4.1-mini-2025-04-14:westeurope - gpt-4.1-mini-2025-04-14:germanywestcentral - gpt-4.1-mini-2025-04-14:polandcentral - gpt-4.1-mini-2025-04-14:spaincentral - gpt-4.1-nano-2025-04-14:westus - gpt-4.1-nano-2025-04-14:eastus2 - gpt-4.1-nano-2025-04-14:westus3 - gpt-4.1-nano-2025-04-14:northcentralus - gpt-4.1-nano-2025-04-14:southcentralus - gpt-4o-2024-11-20:swedencentral - gpt-4o-2024-11-20:westus - gpt-4o-2024-11-20:eastus2 - gpt-4o-2024-11-20:eastus - gpt-4o-2024-11-20:westus3 - gpt-4o-2024-11-20:southcentralus - gpt-4o-2024-11-20:westeurope - gpt-4o-2024-11-20:germanywestcentral - gpt-4o-2024-11-20:polandcentral - gpt-4o-2024-11-20:spaincentral - gpt-4o-2024-08-06:westus - gpt-4o-2024-08-06:westus3 - gpt-4o-2024-08-06:eastus - gpt-4o-2024-08-06:eastus2 - gpt-4o-2024-08-06:northcentralus - gpt-4o-2024-08-06:southcentralus - gpt-4o-mini-2024-07-18:westus - gpt-4o-mini-2024-07-18:westus3 - gpt-4o-mini-2024-07-18:eastus - gpt-4o-mini-2024-07-18:eastus2 - gpt-4o-mini-2024-07-18:northcentralus - gpt-4o-mini-2024-07-18:southcentralus - gpt-4o-2024-05-13:eastus2 - gpt-4o-2024-05-13:eastus - gpt-4o-2024-05-13:northcentralus - gpt-4o-2024-05-13:southcentralus - gpt-4o-2024-05-13:westus3 - gpt-4o-2024-05-13:westus - gpt-4-turbo-2024-04-09:eastus2 - gpt-4-0125-preview:eastus - gpt-4-0125-preview:northcentralus - gpt-4-0125-preview:southcentralus - gpt-4-1106-preview:australiaeast - gpt-4-1106-preview:canadaeast - gpt-4-1106-preview:france - gpt-4-1106-preview:india - gpt-4-1106-preview:norway - gpt-4-1106-preview:swedencentral - gpt-4-1106-preview:uk - gpt-4-1106-preview:westus - gpt-4-1106-preview:westus3 - gpt-4-0613:canadaeast - gpt-3.5-turbo-0125:canadaeast - gpt-3.5-turbo-0125:northcentralus - gpt-3.5-turbo-0125:southcentralus - gpt-3.5-turbo-1106:canadaeast - gpt-3.5-turbo-1106:westus description: >- This is the OpenAI model that will be used. When using Vapi OpenAI or your own Azure Credentials, you have the option to specify the region for the selected model. This shouldn't be specified unless you have a specific reason to do so. Vapi will automatically find the fastest region that make sense. This is helpful when you are required to comply with Data Residency rules. Learn more about Azure regions here https://azure.microsoft.com/en-us/explore/global-infrastructure/data-residency/. @default undefined title: OpenAiModelModel OpenAiModelFallbackModelsItems: type: string enum: - gpt-5.4 - gpt-5.4-mini - gpt-5.4-nano - gpt-5.2 - gpt-5.2-chat-latest - gpt-5.1 - gpt-5.1-chat-latest - gpt-5 - gpt-5-chat-latest - gpt-5-mini - gpt-5-nano - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - chatgpt-4o-latest - o3 - o3-mini - o4-mini - o1-mini - o1-mini-2024-09-12 - gpt-4o-realtime-preview-2024-10-01 - gpt-4o-realtime-preview-2024-12-17 - gpt-4o-mini-realtime-preview-2024-12-17 - gpt-realtime-2025-08-28 - gpt-realtime-mini-2025-12-15 - gpt-4o-mini-2024-07-18 - gpt-4o-mini - gpt-4o - gpt-4o-2024-05-13 - gpt-4o-2024-08-06 - gpt-4o-2024-11-20 - gpt-4-turbo - gpt-4-turbo-2024-04-09 - gpt-4-turbo-preview - gpt-4-0125-preview - gpt-4-1106-preview - gpt-4 - gpt-4-0613 - gpt-3.5-turbo - gpt-3.5-turbo-0125 - gpt-3.5-turbo-1106 - gpt-3.5-turbo-16k - gpt-3.5-turbo-0613 - gpt-4.1-2025-04-14:westus - gpt-4.1-2025-04-14:eastus2 - gpt-4.1-2025-04-14:eastus - gpt-4.1-2025-04-14:westus3 - gpt-4.1-2025-04-14:northcentralus - gpt-4.1-2025-04-14:southcentralus - gpt-4.1-2025-04-14:westeurope - gpt-4.1-2025-04-14:germanywestcentral - gpt-4.1-2025-04-14:polandcentral - gpt-4.1-2025-04-14:spaincentral - gpt-4.1-mini-2025-04-14:westus - gpt-4.1-mini-2025-04-14:eastus2 - gpt-4.1-mini-2025-04-14:eastus - gpt-4.1-mini-2025-04-14:westus3 - gpt-4.1-mini-2025-04-14:northcentralus - gpt-4.1-mini-2025-04-14:southcentralus - gpt-4.1-mini-2025-04-14:westeurope - gpt-4.1-mini-2025-04-14:germanywestcentral - gpt-4.1-mini-2025-04-14:polandcentral - gpt-4.1-mini-2025-04-14:spaincentral - gpt-4.1-nano-2025-04-14:westus - gpt-4.1-nano-2025-04-14:eastus2 - gpt-4.1-nano-2025-04-14:westus3 - gpt-4.1-nano-2025-04-14:northcentralus - gpt-4.1-nano-2025-04-14:southcentralus - gpt-4o-2024-11-20:swedencentral - gpt-4o-2024-11-20:westus - gpt-4o-2024-11-20:eastus2 - gpt-4o-2024-11-20:eastus - gpt-4o-2024-11-20:westus3 - gpt-4o-2024-11-20:southcentralus - gpt-4o-2024-11-20:westeurope - gpt-4o-2024-11-20:germanywestcentral - gpt-4o-2024-11-20:polandcentral - gpt-4o-2024-11-20:spaincentral - gpt-4o-2024-08-06:westus - gpt-4o-2024-08-06:westus3 - gpt-4o-2024-08-06:eastus - gpt-4o-2024-08-06:eastus2 - gpt-4o-2024-08-06:northcentralus - gpt-4o-2024-08-06:southcentralus - gpt-4o-mini-2024-07-18:westus - gpt-4o-mini-2024-07-18:westus3 - gpt-4o-mini-2024-07-18:eastus - gpt-4o-mini-2024-07-18:eastus2 - gpt-4o-mini-2024-07-18:northcentralus - gpt-4o-mini-2024-07-18:southcentralus - gpt-4o-2024-05-13:eastus2 - gpt-4o-2024-05-13:eastus - gpt-4o-2024-05-13:northcentralus - gpt-4o-2024-05-13:southcentralus - gpt-4o-2024-05-13:westus3 - gpt-4o-2024-05-13:westus - gpt-4-turbo-2024-04-09:eastus2 - gpt-4-0125-preview:eastus - gpt-4-0125-preview:northcentralus - gpt-4-0125-preview:southcentralus - gpt-4-1106-preview:australiaeast - gpt-4-1106-preview:canadaeast - gpt-4-1106-preview:france - gpt-4-1106-preview:india - gpt-4-1106-preview:norway - gpt-4-1106-preview:swedencentral - gpt-4-1106-preview:uk - gpt-4-1106-preview:westus - gpt-4-1106-preview:westus3 - gpt-4-0613:canadaeast - gpt-3.5-turbo-0125:canadaeast - gpt-3.5-turbo-0125:northcentralus - gpt-3.5-turbo-0125:southcentralus - gpt-3.5-turbo-1106:canadaeast - gpt-3.5-turbo-1106:westus title: OpenAiModelFallbackModelsItems OpenAiModelToolStrictCompatibilityMode: type: string enum: - strip-parameters-with-unsupported-validation - strip-unsupported-validation description: >- Azure OpenAI doesn't support `maxLength` right now https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/structured-outputs?tabs=python-secure%2Cdotnet-entra-id&pivots=programming-language-csharp#unsupported-type-specific-keywords. Need to strip. - `strip-parameters-with-unsupported-validation` will strip parameters with unsupported validation. - `strip-unsupported-validation` will keep the parameters but strip unsupported validation. @default `strip-unsupported-validation` title: OpenAiModelToolStrictCompatibilityMode OpenAiModelPromptCacheRetention: type: string enum: - in_memory - 24h description: >- This controls the prompt cache retention policy for models that support extended caching (GPT-4.1, GPT-5 series). - `in_memory`: Default behavior, cache retained in GPU memory only - `24h`: Extended caching, keeps cached prefixes active for up to 24 hours by offloading to GPU-local storage Only applies to models: gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.2, gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1-chat-latest, gpt-5, gpt-5-codex, gpt-4.1 @default undefined (uses API default which is 'in_memory') title: OpenAiModelPromptCacheRetention OpenAIModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/OpenAiModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/OpenAiModelKnowledgeBase' description: These are the options for the knowledge base. provider: $ref: '#/components/schemas/OpenAiModelProvider' description: This is the provider that will be used for the model. model: $ref: '#/components/schemas/OpenAiModelModel' description: >- This is the OpenAI model that will be used. When using Vapi OpenAI or your own Azure Credentials, you have the option to specify the region for the selected model. This shouldn't be specified unless you have a specific reason to do so. Vapi will automatically find the fastest region that make sense. This is helpful when you are required to comply with Data Residency rules. Learn more about Azure regions here https://azure.microsoft.com/en-us/explore/global-infrastructure/data-residency/. @default undefined fallbackModels: type: array items: $ref: '#/components/schemas/OpenAiModelFallbackModelsItems' description: >- These are the fallback models that will be used if the primary model fails. This shouldn't be specified unless you have a specific reason to do so. Vapi will automatically find the fastest fallbacks that make sense. toolStrictCompatibilityMode: $ref: '#/components/schemas/OpenAiModelToolStrictCompatibilityMode' description: >- Azure OpenAI doesn't support `maxLength` right now https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/structured-outputs?tabs=python-secure%2Cdotnet-entra-id&pivots=programming-language-csharp#unsupported-type-specific-keywords. Need to strip. - `strip-parameters-with-unsupported-validation` will strip parameters with unsupported validation. - `strip-unsupported-validation` will keep the parameters but strip unsupported validation. @default `strip-unsupported-validation` promptCacheRetention: $ref: '#/components/schemas/OpenAiModelPromptCacheRetention' description: >- This controls the prompt cache retention policy for models that support extended caching (GPT-4.1, GPT-5 series). - `in_memory`: Default behavior, cache retained in GPU memory only - `24h`: Extended caching, keeps cached prefixes active for up to 24 hours by offloading to GPU-local storage Only applies to models: gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.2, gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1-chat-latest, gpt-5, gpt-5-codex, gpt-4.1 @default undefined (uses API default which is 'in_memory') promptCacheKey: type: string description: >- This is the prompt cache key for models that support extended caching (GPT-4.1, GPT-5 series). Providing a cache key allows you to share cached prefixes across requests. @default undefined temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - provider - model title: OpenAIModel OpenRouterModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: OpenRouterModelToolsItems OpenRouterModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: OpenRouterModelKnowledgeBase OpenRouterModelProvider: type: string enum: - openrouter title: OpenRouterModelProvider OpenRouterModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/OpenRouterModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/OpenRouterModelKnowledgeBase' description: These are the options for the knowledge base. provider: $ref: '#/components/schemas/OpenRouterModelProvider' model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - provider - model title: OpenRouterModel PerplexityAiModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: PerplexityAiModelToolsItems PerplexityAiModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: PerplexityAiModelKnowledgeBase PerplexityAiModelProvider: type: string enum: - perplexity-ai title: PerplexityAiModelProvider PerplexityAIModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/PerplexityAiModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/PerplexityAiModelKnowledgeBase' description: These are the options for the knowledge base. provider: $ref: '#/components/schemas/PerplexityAiModelProvider' model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - provider - model title: PerplexityAIModel TogetherAiModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: TogetherAiModelToolsItems TogetherAiModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: TogetherAiModelKnowledgeBase TogetherAiModelProvider: type: string enum: - together-ai title: TogetherAiModelProvider TogetherAIModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/TogetherAiModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/TogetherAiModelKnowledgeBase' description: These are the options for the knowledge base. provider: $ref: '#/components/schemas/TogetherAiModelProvider' model: type: string description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - provider - model title: TogetherAIModel XaiModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: XaiModelToolsItems XaiModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: XaiModelKnowledgeBase XaiModelModel: type: string enum: - grok-beta - grok-2 - grok-3 - grok-4-fast-reasoning - grok-4-fast-non-reasoning description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b title: XaiModelModel XaiModelProvider: type: string enum: - xai title: XaiModelProvider XaiModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/XaiModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/XaiModelKnowledgeBase' description: These are the options for the knowledge base. model: $ref: '#/components/schemas/XaiModelModel' description: >- This is the name of the model. Ex. cognitivecomputations/dolphin-mixtral-8x7b provider: $ref: '#/components/schemas/XaiModelProvider' temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - model - provider title: XaiModel AssistantOverridesModel: oneOf: - $ref: '#/components/schemas/AnthropicModel' - $ref: '#/components/schemas/AnthropicBedrockModel' - $ref: '#/components/schemas/AnyscaleModel' - $ref: '#/components/schemas/CerebrasModel' - $ref: '#/components/schemas/CustomLLMModel' - $ref: '#/components/schemas/DeepInfraModel' - $ref: '#/components/schemas/DeepSeekModel' - $ref: '#/components/schemas/GoogleModel' - $ref: '#/components/schemas/GroqModel' - $ref: '#/components/schemas/InflectionAIModel' - $ref: '#/components/schemas/MinimaxLLMModel' - $ref: '#/components/schemas/OpenAIModel' - $ref: '#/components/schemas/OpenRouterModel' - $ref: '#/components/schemas/PerplexityAIModel' - $ref: '#/components/schemas/TogetherAIModel' - $ref: '#/components/schemas/XaiModel' description: These are the options for the assistant's LLM. title: AssistantOverridesModel AzureVoiceProvider: type: string enum: - azure description: This is the voice provider that will be used. title: AzureVoiceProvider AzureVoiceId0: type: string enum: - andrew - brian - emma title: AzureVoiceId0 AzureVoiceId: oneOf: - $ref: '#/components/schemas/AzureVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: AzureVoiceId ChunkPlanPunctuationBoundaries: type: string enum: - 。 - ， - . - '!' - '?' - ; - ) - ، - ۔ - । - ॥ - '|' - '||' - ',' - ':' description: >- These are the punctuations that are considered valid boundaries for a chunk to be created. Usage: - To increase quality, constrain to fewer boundaries. - To decrease latency, enable all. Default is automatically set to balance the trade-off between quality and latency based on the provider. title: ChunkPlanPunctuationBoundaries ExactReplacementType: type: string enum: - exact description: >- This is the exact replacement type. You can use this to replace a specific word or phrase with a different word or phrase. Usage: - Replace "hello" with "hi": { type: 'exact', key: 'hello', value: 'hi' } - Replace "good morning" with "good day": { type: 'exact', key: 'good morning', value: 'good day' } - Replace a specific name: { type: 'exact', key: 'John Doe', value: 'Jane Smith' } - Replace an acronym: { type: 'exact', key: 'AI', value: 'Artificial Intelligence' } - Replace a company name with its phonetic pronunciation: { type: 'exact', key: 'Vapi', value: 'Vappy' } title: ExactReplacementType ExactReplacement: type: object properties: type: $ref: '#/components/schemas/ExactReplacementType' description: >- This is the exact replacement type. You can use this to replace a specific word or phrase with a different word or phrase. Usage: - Replace "hello" with "hi": { type: 'exact', key: 'hello', value: 'hi' } - Replace "good morning" with "good day": { type: 'exact', key: 'good morning', value: 'good day' } - Replace a specific name: { type: 'exact', key: 'John Doe', value: 'Jane Smith' } - Replace an acronym: { type: 'exact', key: 'AI', value: 'Artificial Intelligence' } - Replace a company name with its phonetic pronunciation: { type: 'exact', key: 'Vapi', value: 'Vappy' } replaceAllEnabled: type: boolean default: false description: >- This option let's you control whether to replace all instances of the key or only the first one. By default, it only replaces the first instance. Examples: - For { type: 'exact', key: 'hello', value: 'hi', replaceAllEnabled: false }. Before: "hello world, hello universe" | After: "hi world, hello universe" - For { type: 'exact', key: 'hello', value: 'hi', replaceAllEnabled: true }. Before: "hello world, hello universe" | After: "hi world, hi universe" @default false key: type: string description: This is the key to replace. value: type: string description: This is the value that will replace the match. required: - type - key - value title: ExactReplacement RegexReplacementType: type: string enum: - regex description: >- This is the regex replacement type. You can use this to replace a word or phrase that matches a pattern. Usage: - Replace all numbers with "some number": { type: 'regex', regex: '\\d+', value: 'some number' } - Replace email addresses with "[EMAIL]": { type: 'regex', regex: '\\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Z|a-z]{2,}\\b', value: '[EMAIL]' } - Replace phone numbers with a formatted version: { type: 'regex', regex: '(\\d{3})(\\d{3})(\\d{4})', value: '($1) $2-$3' } - Replace all instances of "color" or "colour" with "hue": { type: 'regex', regex: 'colou?r', value: 'hue' } - Capitalize the first letter of every sentence: { type: 'regex', regex: '(?<=\\. |^)[a-z]', value: (match) => match.toUpperCase() } title: RegexReplacementType RegexOptionType: type: string enum: - ignore-case - whole-word - multi-line description: |- This is the type of the regex option. Options are: - `ignore-case`: Ignores the case of the text being matched. Add - `whole-word`: Matches whole words only. - `multi-line`: Matches across multiple lines. title: RegexOptionType RegexOption: type: object properties: type: $ref: '#/components/schemas/RegexOptionType' description: |- This is the type of the regex option. Options are: - `ignore-case`: Ignores the case of the text being matched. Add - `whole-word`: Matches whole words only. - `multi-line`: Matches across multiple lines. enabled: type: boolean description: |- This is whether to enable the option. @default false required: - type - enabled title: RegexOption RegexReplacement: type: object properties: type: $ref: '#/components/schemas/RegexReplacementType' description: >- This is the regex replacement type. You can use this to replace a word or phrase that matches a pattern. Usage: - Replace all numbers with "some number": { type: 'regex', regex: '\\d+', value: 'some number' } - Replace email addresses with "[EMAIL]": { type: 'regex', regex: '\\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Z|a-z]{2,}\\b', value: '[EMAIL]' } - Replace phone numbers with a formatted version: { type: 'regex', regex: '(\\d{3})(\\d{3})(\\d{4})', value: '($1) $2-$3' } - Replace all instances of "color" or "colour" with "hue": { type: 'regex', regex: 'colou?r', value: 'hue' } - Capitalize the first letter of every sentence: { type: 'regex', regex: '(?<=\\. |^)[a-z]', value: (match) => match.toUpperCase() } regex: type: string description: >- This is the regex pattern to replace. Note: - This works by using the `string.replace` method in Node.JS. Eg. `"hello there".replace(/hello/g, "hi")` will return `"hi there"`. Hot tip: - In JavaScript, escape `\` when sending the regex pattern. Eg. `"hello\sthere"` will be sent over the wire as `"hellosthere"`. Send `"hello\\sthere"` instead. options: type: array items: $ref: '#/components/schemas/RegexOption' description: >- These are the options for the regex replacement. Defaults to all disabled. @default [] value: type: string description: This is the value that will replace the match. required: - type - regex - value title: RegexReplacement FormatPlanReplacementsItems: oneOf: - $ref: '#/components/schemas/ExactReplacement' - $ref: '#/components/schemas/RegexReplacement' title: FormatPlanReplacementsItems FormatPlanFormattersEnabled: type: string enum: - markdown - asterisk - quote - dash - newline - colon - acronym - dollarAmount - email - date - time - distance - unit - percentage - phoneNumber - number - stripAsterisk description: >- List of formatters to apply. If not provided, all default formatters will be applied. If provided, only the specified formatters will be applied. Note: Some essential formatters like angle bracket removal will always be applied. @default undefined title: FormatPlanFormattersEnabled FormatPlan: type: object properties: enabled: type: boolean description: >- This determines whether the chunk is formatted before being sent to the voice provider. This helps with enunciation. This includes phone numbers, emails and addresses. Default `true`. Usage: - To rely on the voice provider's formatting logic, set this to `false`. If `voice.chunkPlan.enabled` is `false`, this is automatically `false` since there's no chunk to format. @default true numberToDigitsCutoff: type: number format: double description: >- This is the cutoff after which a number is converted to individual digits instead of being spoken as words. Example: - If cutoff 2025, "12345" is converted to "1 2 3 4 5" while "1200" is converted to "twelve hundred". Usage: - If your use case doesn't involve IDs like zip codes, set this to a high value. - If your use case involves IDs that are shorter than 5 digits, set this to a lower value. @default 2025 replacements: type: array items: $ref: '#/components/schemas/FormatPlanReplacementsItems' description: >- These are the custom replacements you can make to the chunk before it is sent to the voice provider. Usage: - To replace a specific word or phrase with a different word or phrase, use the `ExactReplacement` type. Eg. `{ type: 'exact', key: 'hello', value: 'hi' }` - To replace a word or phrase that matches a pattern, use the `RegexReplacement` type. Eg. `{ type: 'regex', regex: '\\b[a-zA-Z]{5}\\b', value: 'hi' }` @default [] formattersEnabled: $ref: '#/components/schemas/FormatPlanFormattersEnabled' description: >- List of formatters to apply. If not provided, all default formatters will be applied. If provided, only the specified formatters will be applied. Note: Some essential formatters like angle bracket removal will always be applied. @default undefined title: FormatPlan ChunkPlan: type: object properties: enabled: type: boolean description: >- This determines whether the model output is chunked before being sent to the voice provider. Default `true`. Usage: - To rely on the voice provider's audio generation logic, set this to `false`. - If seeing issues with quality, set this to `true`. If disabled, Vapi-provided audio control tokens like will not work. @default true minCharacters: type: number format: double description: |- This is the minimum number of characters in a chunk. Usage: - To increase quality, set this to a higher value. - To decrease latency, set this to a lower value. @default 30 punctuationBoundaries: $ref: '#/components/schemas/ChunkPlanPunctuationBoundaries' description: >- These are the punctuations that are considered valid boundaries for a chunk to be created. Usage: - To increase quality, constrain to fewer boundaries. - To decrease latency, enable all. Default is automatically set to balance the trade-off between quality and latency based on the provider. formatPlan: $ref: '#/components/schemas/FormatPlan' description: >- This is the plan for formatting the chunk before it is sent to the voice provider. title: ChunkPlan FallbackAzureVoiceProvider: type: string enum: - azure description: This is the voice provider that will be used. title: FallbackAzureVoiceProvider FallbackAzureVoiceId0: type: string enum: - andrew - brian - emma title: FallbackAzureVoiceId0 FallbackAzureVoiceId: oneOf: - $ref: '#/components/schemas/FallbackAzureVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: FallbackAzureVoiceId FallbackAzureVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackAzureVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackAzureVoiceId' description: This is the provider-specific ID that will be used. speed: type: number format: double description: This is the speed multiplier that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. oneOf: description: Any type required: - provider - voiceId title: FallbackAzureVoice FallbackCartesiaVoiceProvider: type: string enum: - cartesia description: This is the voice provider that will be used. title: FallbackCartesiaVoiceProvider FallbackCartesiaVoiceModel: type: string enum: - sonic-3 - sonic-3-2026-01-12 - sonic-3-2025-10-27 - sonic-2 - sonic-2-2025-06-11 - sonic-english - sonic-multilingual - sonic-preview - sonic description: >- This is the model that will be used. This is optional and will default to the correct model for the voiceId. title: FallbackCartesiaVoiceModel FallbackCartesiaVoiceLanguage: type: string enum: - ar - bg - bn - cs - da - de - el - en - es - fi - fr - gu - he - hi - hr - hu - id - it - ja - ka - kn - ko - ml - mr - ms - nl - 'no' - pa - pl - pt - ro - ru - sk - sv - ta - te - th - tl - tr - uk - vi - zh description: >- This is the language that will be used. This is optional and will default to the correct language for the voiceId. title: FallbackCartesiaVoiceLanguage CartesiaSpeedControl0: type: string enum: - slowest - slow - normal - fast - fastest title: CartesiaSpeedControl0 CartesiaSpeedControl: oneOf: - $ref: '#/components/schemas/CartesiaSpeedControl0' - type: number format: double title: CartesiaSpeedControl CartesiaExperimentalControlsEmotion: type: string enum: - anger:lowest - anger:low - anger:high - anger:highest - positivity:lowest - positivity:low - positivity:high - positivity:highest - surprise:lowest - surprise:low - surprise:high - surprise:highest - sadness:lowest - sadness:low - sadness:high - sadness:highest - curiosity:lowest - curiosity:low - curiosity:high - curiosity:highest title: CartesiaExperimentalControlsEmotion CartesiaExperimentalControls: type: object properties: speed: $ref: '#/components/schemas/CartesiaSpeedControl' emotion: $ref: '#/components/schemas/CartesiaExperimentalControlsEmotion' title: CartesiaExperimentalControls CartesiaGenerationConfigExperimental: type: object properties: accentLocalization: type: integer default: 0 description: >- Toggle accent localization for sonic-3: 0 (disabled, default) or 1 (enabled). When enabled, the voice adapts to match the transcript language accent while preserving vocal characteristics. title: CartesiaGenerationConfigExperimental CartesiaGenerationConfig: type: object properties: speed: type: number format: double default: 1 description: >- Fine-grained speed control for sonic-3. Only available for sonic-3 model. volume: type: number format: double default: 1 description: >- Fine-grained volume control for sonic-3. Only available for sonic-3 model. experimental: $ref: '#/components/schemas/CartesiaGenerationConfigExperimental' description: >- Experimental model controls for sonic-3. These are subject to breaking changes. title: CartesiaGenerationConfig FallbackCartesiaVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackCartesiaVoiceProvider' description: This is the voice provider that will be used. voiceId: type: string description: The ID of the particular voice you want to use. model: $ref: '#/components/schemas/FallbackCartesiaVoiceModel' description: >- This is the model that will be used. This is optional and will default to the correct model for the voiceId. language: $ref: '#/components/schemas/FallbackCartesiaVoiceLanguage' description: >- This is the language that will be used. This is optional and will default to the correct language for the voiceId. experimentalControls: $ref: '#/components/schemas/CartesiaExperimentalControls' description: Experimental controls for Cartesia voice generation generationConfig: $ref: '#/components/schemas/CartesiaGenerationConfig' description: >- Generation config for fine-grained control of sonic-3 voice output (speed, volume, and experimental controls). Only available for sonic-3 model. pronunciationDictId: type: string description: >- Pronunciation dictionary ID for sonic-3. Allows custom pronunciations for specific words. Only available for sonic-3 model. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackCartesiaVoice FallbackHumeVoiceProvider: type: string enum: - hume description: This is the voice provider that will be used. title: FallbackHumeVoiceProvider FallbackHumeVoiceModel: type: string enum: - octave - octave2 description: This is the model that will be used. title: FallbackHumeVoiceModel FallbackHumeVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackHumeVoiceProvider' description: This is the voice provider that will be used. model: $ref: '#/components/schemas/FallbackHumeVoiceModel' description: This is the model that will be used. voiceId: type: string description: The ID of the particular voice you want to use. isCustomHumeVoice: type: boolean description: >- Indicates whether the chosen voice is a preset Hume AI voice or a custom voice. description: type: string description: >- Natural language instructions describing how the synthesized speech should sound, including but not limited to tone, intonation, pacing, and accent (e.g., 'a soft, gentle voice with a strong British accent'). If a Voice is specified in the request, this description serves as acting instructions. If no Voice is specified, a new voice is generated based on this description. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackHumeVoice FallbackCustomVoiceProvider: type: string enum: - custom-voice description: >- This is the voice provider that will be used. Use `custom-voice` for providers that are not natively supported. title: FallbackCustomVoiceProvider FallbackCustomVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackCustomVoiceProvider' description: >- This is the voice provider that will be used. Use `custom-voice` for providers that are not natively supported. voiceId: type: string description: >- This is the provider-specific ID that will be used. This is passed in the voice request payload to identify the voice to use. server: $ref: '#/components/schemas/Server' description: >- This is where the voice request will be sent. Request Example: POST https://{server.url} Content-Type: application/json { "message": { "type": "voice-request", "text": "Hello, world!", "sampleRate": 24000, ...other metadata about the call... } } Response Expected: 1-channel 16-bit raw PCM audio at the sample rate specified in the request. Here is how the response will be piped to the transport: ``` response.on('data', (chunk: Buffer) => { outputStream.write(chunk); }); ``` chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - server title: FallbackCustomVoice FallbackDeepgramVoiceProvider: type: string enum: - deepgram description: This is the voice provider that will be used. title: FallbackDeepgramVoiceProvider FallbackDeepgramVoiceId: type: string enum: - asteria - luna - stella - athena - hera - orion - arcas - perseus - angus - orpheus - helios - zeus - thalia - andromeda - helena - apollo - arcas - aries - amalthea - asteria - athena - atlas - aurora - callista - cora - cordelia - delia - draco - electra - harmonia - hera - hermes - hyperion - iris - janus - juno - jupiter - luna - mars - minerva - neptune - odysseus - ophelia - orion - orpheus - pandora - phoebe - pluto - saturn - selene - theia - vesta - zeus - celeste - estrella - nestor - sirio - carina - alvaro - diana - aquila - selena - javier description: This is the provider-specific ID that will be used. title: FallbackDeepgramVoiceId FallbackDeepgramVoiceModel: type: string enum: - aura - aura-2 description: >- This is the model that will be used. Defaults to 'aura-2' when not specified. title: FallbackDeepgramVoiceModel FallbackDeepgramVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackDeepgramVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackDeepgramVoiceId' description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/FallbackDeepgramVoiceModel' description: >- This is the model that will be used. Defaults to 'aura-2' when not specified. mipOptOut: type: boolean default: false description: >- If set to true, this will add mip_opt_out=true as a query parameter of all API requests. See https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#want-to-opt-out This will only be used if you are using your own Deepgram API key. @default false chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackDeepgramVoice FallbackElevenLabsVoiceId0: type: string enum: - burt - marissa - andrea - sarah - phillip - steve - joseph - myra - paula - ryan - drew - paul - mrb - matilda - mark title: FallbackElevenLabsVoiceId0 FallbackElevenLabsVoiceId: oneOf: - $ref: '#/components/schemas/FallbackElevenLabsVoiceId0' - type: string description: >- This is the provider-specific ID that will be used. Ensure the Voice is present in your 11Labs Voice Library. title: FallbackElevenLabsVoiceId FallbackElevenLabsVoiceModel: type: string enum: - eleven_multilingual_v2 - eleven_turbo_v2 - eleven_turbo_v2_5 - eleven_flash_v2 - eleven_flash_v2_5 - eleven_monolingual_v1 - eleven_v3 description: >- This is the model that will be used. Defaults to 'eleven_turbo_v2' if not specified. title: FallbackElevenLabsVoiceModel ElevenLabsPronunciationDictionaryLocator: type: object properties: pronunciationDictionaryId: type: string description: This is the ID of the pronunciation dictionary to use. versionId: type: string description: This is the version ID of the pronunciation dictionary to use. required: - pronunciationDictionaryId - versionId title: ElevenLabsPronunciationDictionaryLocator FallbackElevenLabsVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: type: string enum: - 11labs description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackElevenLabsVoiceId' description: >- This is the provider-specific ID that will be used. Ensure the Voice is present in your 11Labs Voice Library. stability: type: number format: double description: Defines the stability for voice settings. similarityBoost: type: number format: double description: Defines the similarity boost for voice settings. style: type: number format: double description: Defines the style for voice settings. useSpeakerBoost: type: boolean description: Defines the use speaker boost for voice settings. speed: type: number format: double description: Defines the speed for voice settings. optimizeStreamingLatency: type: number format: double description: >- Defines the optimize streaming latency for voice settings. Defaults to 3. enableSsmlParsing: type: boolean description: >- This enables the use of https://elevenlabs.io/docs/speech-synthesis/prompting#pronunciation. Defaults to false to save latency. @default false autoMode: type: boolean description: Defines the auto mode for voice settings. Defaults to false. model: $ref: '#/components/schemas/FallbackElevenLabsVoiceModel' description: >- This is the model that will be used. Defaults to 'eleven_turbo_v2' if not specified. language: type: string description: >- This is the language (ISO 639-1) that is enforced for the model. Currently only Turbo v2.5 supports language enforcement. For other models, an error will be returned if language code is provided. pronunciationDictionaryLocators: type: array items: $ref: '#/components/schemas/ElevenLabsPronunciationDictionaryLocator' description: This is the pronunciation dictionary locators to use. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackElevenLabsVoice FallbackVapiVoiceProvider: type: string enum: - vapi description: This is the voice provider that will be used. title: FallbackVapiVoiceProvider FallbackVapiVoiceVoiceId: type: string enum: - Clara - Godfrey - Layla - Sid - Gustavo - Elliot - Kylie - Rohan - Lily - Savannah - Hana - Neha - Cole - Harry - Paige - Spencer - Nico - Kai - Emma - Sagar - Neil - Naina - Leah - Tara - Jess - Leo - Dan - Mia - Zac - Zoe description: The voices provided by Vapi title: FallbackVapiVoiceVoiceId VapiPronunciationDictionaryLocator: type: object properties: pronunciationDictId: type: string description: The pronunciation dictionary ID versionId: type: string description: Version ID (only required for ElevenLabs, ignored for Cartesia) required: - pronunciationDictId title: VapiPronunciationDictionaryLocator FallbackVapiVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackVapiVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackVapiVoiceVoiceId' description: The voices provided by Vapi speed: type: number format: double default: 1 description: |- This is the speed multiplier that will be used. @default 1 pronunciationDictionary: type: array items: $ref: '#/components/schemas/VapiPronunciationDictionaryLocator' description: >- List of pronunciation dictionary locators for custom word pronunciations. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackVapiVoice FallbackLmntVoiceProvider: type: string enum: - lmnt description: This is the voice provider that will be used. title: FallbackLmntVoiceProvider FallbackLmntVoiceId0: type: string enum: - amy - ansel - autumn - ava - brandon - caleb - cassian - chloe - dalton - daniel - dustin - elowen - evander - huxley - james - juniper - kennedy - lauren - leah - lily - lucas - magnus - miles - morgan - natalie - nathan - noah - nyssa - oliver - paige - ryan - sadie - sophie - stella - terrence - tyler - vesper - violet - warrick - zain - zeke - zoe title: FallbackLmntVoiceId0 FallbackLMNTVoiceId: oneOf: - $ref: '#/components/schemas/FallbackLmntVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: FallbackLMNTVoiceId FallbackLmntVoiceLanguage: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu - auto description: Two letter ISO 639-1 language code. Use "auto" for auto-detection. title: FallbackLmntVoiceLanguage FallbackLMNTVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackLmntVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackLMNTVoiceId' description: This is the provider-specific ID that will be used. speed: type: number format: double description: This is the speed multiplier that will be used. language: $ref: '#/components/schemas/FallbackLmntVoiceLanguage' description: Two letter ISO 639-1 language code. Use "auto" for auto-detection. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackLMNTVoice FallbackOpenAiVoiceProvider: type: string enum: - openai description: This is the voice provider that will be used. title: FallbackOpenAiVoiceProvider FallbackOpenAiVoiceId0: type: string enum: - alloy - echo - fable - onyx - nova - shimmer - marin - cedar title: FallbackOpenAiVoiceId0 FallbackOpenAIVoiceId: oneOf: - $ref: '#/components/schemas/FallbackOpenAiVoiceId0' - type: string description: >- This is the provider-specific ID that will be used. Please note that ash, ballad, coral, sage, and verse may only be used with realtime models. title: FallbackOpenAIVoiceId FallbackOpenAiVoiceModel: type: string enum: - tts-1 - tts-1-hd - gpt-4o-mini-tts description: This is the model that will be used for text-to-speech. title: FallbackOpenAiVoiceModel FallbackOpenAIVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackOpenAiVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackOpenAIVoiceId' description: >- This is the provider-specific ID that will be used. Please note that ash, ballad, coral, sage, and verse may only be used with realtime models. model: $ref: '#/components/schemas/FallbackOpenAiVoiceModel' description: This is the model that will be used for text-to-speech. instructions: type: string description: >- This is a prompt that allows you to control the voice of your generated audio. Does not work with 'tts-1' or 'tts-1-hd' models. speed: type: number format: double description: This is the speed multiplier that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackOpenAIVoice FallbackPlayHtVoiceProvider: type: string enum: - playht description: This is the voice provider that will be used. title: FallbackPlayHtVoiceProvider FallbackPlayHtVoiceId0: type: string enum: - jennifer - melissa - will - chris - matt - jack - ruby - davis - donna - michael title: FallbackPlayHtVoiceId0 FallbackPlayHTVoiceId: oneOf: - $ref: '#/components/schemas/FallbackPlayHtVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: FallbackPlayHTVoiceId FallbackPlayHtVoiceEmotion: type: string enum: - female_happy - female_sad - female_angry - female_fearful - female_disgust - female_surprised - male_happy - male_sad - male_angry - male_fearful - male_disgust - male_surprised description: An emotion to be applied to the speech. title: FallbackPlayHtVoiceEmotion FallbackPlayHtVoiceModel: type: string enum: - PlayHT2.0 - PlayHT2.0-turbo - Play3.0-mini - PlayDialog description: Playht voice model/engine to use. title: FallbackPlayHtVoiceModel FallbackPlayHtVoiceLanguage: type: string enum: - afrikaans - albanian - amharic - arabic - bengali - bulgarian - catalan - croatian - czech - danish - dutch - english - french - galician - german - greek - hebrew - hindi - hungarian - indonesian - italian - japanese - korean - malay - mandarin - polish - portuguese - russian - serbian - spanish - swedish - tagalog - thai - turkish - ukrainian - urdu - xhosa description: The language to use for the speech. title: FallbackPlayHtVoiceLanguage FallbackPlayHTVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackPlayHtVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackPlayHTVoiceId' description: This is the provider-specific ID that will be used. speed: type: number format: double description: This is the speed multiplier that will be used. temperature: type: number format: double description: >- A floating point number between 0, exclusive, and 2, inclusive. If equal to null or not provided, the model's default temperature will be used. The temperature parameter controls variance. Lower temperatures result in more predictable results, higher temperatures allow each run to vary more, so the voice may sound less like the baseline voice. emotion: $ref: '#/components/schemas/FallbackPlayHtVoiceEmotion' description: An emotion to be applied to the speech. voiceGuidance: type: number format: double description: >- A number between 1 and 6. Use lower numbers to reduce how unique your chosen voice will be compared to other voices. styleGuidance: type: number format: double description: >- A number between 1 and 30. Use lower numbers to to reduce how strong your chosen emotion will be. Higher numbers will create a very emotional performance. textGuidance: type: number format: double description: >- A number between 1 and 2. This number influences how closely the generated speech adheres to the input text. Use lower values to create more fluid speech, but with a higher chance of deviating from the input text. Higher numbers will make the generated speech more accurate to the input text, ensuring that the words spoken align closely with the provided text. model: $ref: '#/components/schemas/FallbackPlayHtVoiceModel' description: Playht voice model/engine to use. language: $ref: '#/components/schemas/FallbackPlayHtVoiceLanguage' description: The language to use for the speech. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackPlayHTVoice FallbackWellSaidVoiceProvider: type: string enum: - wellsaid description: This is the voice provider that will be used. title: FallbackWellSaidVoiceProvider FallbackWellSaidVoiceModel: type: string enum: - caruso - legacy description: This is the model that will be used. title: FallbackWellSaidVoiceModel FallbackWellSaidVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackWellSaidVoiceProvider' description: This is the voice provider that will be used. voiceId: type: string description: The WellSaid speaker ID to synthesize. model: $ref: '#/components/schemas/FallbackWellSaidVoiceModel' description: This is the model that will be used. enableSsml: type: boolean description: Enables limited SSML translation for input text. libraryIds: type: array items: type: string description: Array of library IDs to use for voice synthesis. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackWellSaidVoice FallbackRimeAiVoiceProvider: type: string enum: - rime-ai description: This is the voice provider that will be used. title: FallbackRimeAiVoiceProvider FallbackRimeAiVoiceId0: type: string enum: - cove - moon - wildflower - eva - amber - maya - lagoon - breeze - helen - joy - marsh - creek - cedar - alpine - summit - nicholas - tyler - colin - hank - thunder - astra - eucalyptus - moraine - peak - tundra - mesa_extra - talon - marlu - glacier - falcon - luna - celeste - estelle - andromeda - esther - lyra - lintel - oculus - vespera - transom - bond - arcade - atrium - cupola - fern - sirius - orion - masonry - albion - parapet description: >- Popular Rime AI voices across mist, mistv2, and arcana models. Any valid Rime AI voice ID is accepted, not just these suggestions. title: FallbackRimeAiVoiceId0 FallbackRimeAIVoiceId: oneOf: - $ref: '#/components/schemas/FallbackRimeAiVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: FallbackRimeAIVoiceId FallbackRimeAiVoiceModel: type: string enum: - arcana - mistv2 - mist description: >- This is the model that will be used. Defaults to 'arcana' when not specified. title: FallbackRimeAiVoiceModel FallbackRimeAiVoiceLanguage: type: string enum: - en - es - de - fr - ar - hi - ja - he - pt - ta - si description: >- Language for speech synthesis. Uses ISO 639 codes. Supported: en, es, de, fr, ar, hi, ja, he, pt, ta, si. title: FallbackRimeAiVoiceLanguage FallbackRimeAIVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackRimeAiVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackRimeAIVoiceId' description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/FallbackRimeAiVoiceModel' description: >- This is the model that will be used. Defaults to 'arcana' when not specified. speed: type: number format: double description: This is the speed multiplier that will be used. pauseBetweenBrackets: type: boolean description: >- This is a flag that controls whether to add slight pauses using angle brackets. Example: "Hi. <200> I'd love to have a conversation with you." adds a 200ms pause between the first and second sentences. phonemizeBetweenBrackets: type: boolean description: >- This is a flag that controls whether text inside brackets should be phonemized (converted to phonetic pronunciation) - Example: "{h'El.o} World" will pronounce "Hello" as expected. reduceLatency: type: boolean description: >- This is a flag that controls whether to optimize for reduced latency in streaming. https://docs.rime.ai/api-reference/endpoint/websockets#param-reduce-latency inlineSpeedAlpha: type: string description: >- This is a string that allows inline speed control using alpha notation. https://docs.rime.ai/api-reference/endpoint/websockets#param-inline-speed-alpha language: $ref: '#/components/schemas/FallbackRimeAiVoiceLanguage' description: >- Language for speech synthesis. Uses ISO 639 codes. Supported: en, es, de, fr, ar, hi, ja, he, pt, ta, si. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackRimeAIVoice FallbackSmallestAiVoiceProvider: type: string enum: - smallest-ai description: This is the voice provider that will be used. title: FallbackSmallestAiVoiceProvider FallbackSmallestAiVoiceId0: type: string enum: - emily - jasmine - arman - james - mithali - aravind - raj - diya - raman - ananya - isha - william - aarav - monika - niharika - deepika - raghav - kajal - radhika - mansi - nisha - saurabh - pooja - saina - sanya title: FallbackSmallestAiVoiceId0 FallbackSmallestAIVoiceId: oneOf: - $ref: '#/components/schemas/FallbackSmallestAiVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: FallbackSmallestAIVoiceId FallbackSmallestAiVoiceModel: type: string enum: - lightning description: >- Smallest AI voice model to use. Defaults to 'lightning' when not specified. title: FallbackSmallestAiVoiceModel FallbackSmallestAIVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackSmallestAiVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackSmallestAIVoiceId' description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/FallbackSmallestAiVoiceModel' description: >- Smallest AI voice model to use. Defaults to 'lightning' when not specified. speed: type: number format: double description: This is the speed multiplier that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackSmallestAIVoice FallbackTavusVoiceProvider: type: string enum: - tavus description: This is the voice provider that will be used. title: FallbackTavusVoiceProvider FallbackTavusVoiceVoiceId0: type: string enum: - r52da2535a title: FallbackTavusVoiceVoiceId0 FallbackTavusVoiceVoiceId: oneOf: - $ref: '#/components/schemas/FallbackTavusVoiceVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: FallbackTavusVoiceVoiceId TavusConversationProperties: type: object properties: maxCallDuration: type: number format: double description: >- The maximum duration of the call in seconds. The default `maxCallDuration` is 3600 seconds (1 hour). Once the time limit specified by this parameter has been reached, the conversation will automatically shut down. participantLeftTimeout: type: number format: double description: >- The duration in seconds after which the call will be automatically shut down once the last participant leaves. participantAbsentTimeout: type: number format: double description: >- Starting from conversation creation, the duration in seconds after which the call will be automatically shut down if no participant joins the call. Default is 300 seconds (5 minutes). enableRecording: type: boolean description: If true, the user will be able to record the conversation. enableTranscription: type: boolean description: >- If true, the user will be able to transcribe the conversation. You can find more instructions on displaying transcriptions if you are using your custom DailyJS components here. You need to have an event listener on Daily that listens for `app-messages`. applyGreenscreen: type: boolean description: >- If true, the background will be replaced with a greenscreen (RGB values: `[0, 255, 155]`). You can use WebGL on the frontend to make the greenscreen transparent or change its color. language: type: string description: >- The language of the conversation. Please provide the **full language name**, not the two-letter code. If you are using your own TTS voice, please ensure it supports the language you provide. If you are using a stock replica or default persona, please note that only ElevenLabs and Cartesia supported languages are available. You can find a full list of supported languages for Cartesia here, for ElevenLabs here, and for PlayHT here. recordingS3BucketName: type: string description: The name of the S3 bucket where the recording will be stored. recordingS3BucketRegion: type: string description: The region of the S3 bucket where the recording will be stored. awsAssumeRoleArn: type: string description: The ARN of the role that will be assumed to access the S3 bucket. title: TavusConversationProperties FallbackTavusVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackTavusVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackTavusVoiceVoiceId' description: This is the provider-specific ID that will be used. personaId: type: string description: >- This is the unique identifier for the persona that the replica will use in the conversation. callbackUrl: type: string description: >- This is the url that will receive webhooks with updates regarding the conversation state. conversationName: type: string description: This is the name for the conversation. conversationalContext: type: string description: >- This is the context that will be appended to any context provided in the persona, if one is provided. customGreeting: type: string description: >- This is the custom greeting that the replica will give once a participant joines the conversation. properties: $ref: '#/components/schemas/TavusConversationProperties' description: These are optional properties used to customize the conversation. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackTavusVoice FallbackNeuphonicVoiceProvider: type: string enum: - neuphonic description: This is the voice provider that will be used. title: FallbackNeuphonicVoiceProvider FallbackNeuphonicVoiceModel: type: string enum: - neu_hq - neu_fast description: >- This is the model that will be used. Defaults to 'neu_fast' if not specified. title: FallbackNeuphonicVoiceModel FallbackNeuphonicVoiceLanguage: type: object properties: {} description: This is the language (ISO 639-1) that is enforced for the model. title: FallbackNeuphonicVoiceLanguage FallbackNeuphonicVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackNeuphonicVoiceProvider' description: This is the voice provider that will be used. voiceId: type: string description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/FallbackNeuphonicVoiceModel' description: >- This is the model that will be used. Defaults to 'neu_fast' if not specified. language: $ref: '#/components/schemas/FallbackNeuphonicVoiceLanguage' description: This is the language (ISO 639-1) that is enforced for the model. speed: type: number format: double description: This is the speed multiplier that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId - language title: FallbackNeuphonicVoice FallbackSesameVoiceProvider: type: string enum: - sesame description: This is the voice provider that will be used. title: FallbackSesameVoiceProvider FallbackSesameVoiceModel: type: string enum: - csm-1b description: This is the model that will be used. title: FallbackSesameVoiceModel FallbackSesameVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackSesameVoiceProvider' description: This is the voice provider that will be used. voiceId: type: string description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/FallbackSesameVoiceModel' description: This is the model that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId - model title: FallbackSesameVoice FallbackInworldVoiceProvider: type: string enum: - inworld description: This is the voice provider that will be used. title: FallbackInworldVoiceProvider FallbackInworldVoiceVoiceId: type: string enum: - Alex - Ashley - Craig - Deborah - Dennis - Edward - Elizabeth - Hades - Julia - Pixie - Mark - Olivia - Priya - Ronald - Sarah - Shaun - Theodore - Timothy - Wendy - Dominus - Hana - Clive - Carter - Blake - Luna - Yichen - Xiaoyin - Xinyi - Jing - Erik - Katrien - Lennart - Lore - Alain - Hélène - Mathieu - Étienne - Johanna - Josef - Gianni - Orietta - Asuka - Satoshi - Hyunwoo - Minji - Seojun - Yoona - Szymon - Wojciech - Heitor - Maitê - Diego - Lupita - Miguel - Rafael - Svetlana - Elena - Dmitry - Nikolai - Riya - Manoj - Yael - Oren - Nour - Omar description: >- Available voices by language: • en: Alex, Ashley, Craig, Deborah, Dennis, Edward, Elizabeth, Hades, Julia, Pixie, Mark, Olivia, Priya, Ronald, Sarah, Shaun, Theodore, Timothy, Wendy, Dominus, Hana, Clive, Carter, Blake, Luna • zh: Yichen, Xiaoyin, Xinyi, Jing • nl: Erik, Katrien, Lennart, Lore • fr: Alain, Hélène, Mathieu, Étienne • de: Johanna, Josef • it: Gianni, Orietta • ja: Asuka, Satoshi • ko: Hyunwoo, Minji, Seojun, Yoona • pl: Szymon, Wojciech • pt: Heitor, Maitê • es: Diego, Lupita, Miguel, Rafael • ru: Svetlana, Elena, Dmitry, Nikolai • hi: Riya, Manoj • he: Yael, Oren • ar: Nour, Omar title: FallbackInworldVoiceVoiceId FallbackInworldVoiceModel: type: string enum: - inworld-tts-1 default: inworld-tts-1 description: This is the model that will be used. title: FallbackInworldVoiceModel FallbackInworldVoiceLanguageCode: type: string enum: - en - zh - ko - nl - fr - es - ja - de - it - pl - pt - ru - hi - he - ar default: en description: Language code for Inworld TTS synthesis title: FallbackInworldVoiceLanguageCode FallbackInworldVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/FallbackInworldVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/FallbackInworldVoiceVoiceId' description: >- Available voices by language: • en: Alex, Ashley, Craig, Deborah, Dennis, Edward, Elizabeth, Hades, Julia, Pixie, Mark, Olivia, Priya, Ronald, Sarah, Shaun, Theodore, Timothy, Wendy, Dominus, Hana, Clive, Carter, Blake, Luna • zh: Yichen, Xiaoyin, Xinyi, Jing • nl: Erik, Katrien, Lennart, Lore • fr: Alain, Hélène, Mathieu, Étienne • de: Johanna, Josef • it: Gianni, Orietta • ja: Asuka, Satoshi • ko: Hyunwoo, Minji, Seojun, Yoona • pl: Szymon, Wojciech • pt: Heitor, Maitê • es: Diego, Lupita, Miguel, Rafael • ru: Svetlana, Elena, Dmitry, Nikolai • hi: Riya, Manoj • he: Yael, Oren • ar: Nour, Omar model: $ref: '#/components/schemas/FallbackInworldVoiceModel' description: This is the model that will be used. languageCode: $ref: '#/components/schemas/FallbackInworldVoiceLanguageCode' description: Language code for Inworld TTS synthesis temperature: type: number format: double default: 1.1 description: >- A floating point number between 0, exclusive, and 2, inclusive. If equal to null or not provided, the model's default temperature of 1.1 will be used. The temperature parameter controls variance. Higher values will make the output more random and can lead to more expressive results. Lower values will make it more deterministic. See https://docs.inworld.ai/docs/tts/capabilities/generating-audio#additional-configurations for more details. speakingRate: type: number format: double default: 1 description: >- A floating point number between 0.5, inclusive, and 1.5, inclusive. If equal to null or not provided, the model's default speaking speed of 1.0 will be used. Values above 0.8 are recommended for higher quality. See https://docs.inworld.ai/docs/tts/capabilities/generating-audio#additional-configurations for more details. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. required: - provider - voiceId title: FallbackInworldVoice FallbackPlanVoicesItems: oneOf: - $ref: '#/components/schemas/FallbackAzureVoice' - $ref: '#/components/schemas/FallbackCartesiaVoice' - $ref: '#/components/schemas/FallbackHumeVoice' - $ref: '#/components/schemas/FallbackCustomVoice' - $ref: '#/components/schemas/FallbackDeepgramVoice' - $ref: '#/components/schemas/FallbackElevenLabsVoice' - $ref: '#/components/schemas/FallbackVapiVoice' - $ref: '#/components/schemas/FallbackLMNTVoice' - $ref: '#/components/schemas/FallbackOpenAIVoice' - $ref: '#/components/schemas/FallbackPlayHTVoice' - $ref: '#/components/schemas/FallbackWellSaidVoice' - $ref: '#/components/schemas/FallbackRimeAIVoice' - $ref: '#/components/schemas/FallbackSmallestAIVoice' - $ref: '#/components/schemas/FallbackTavusVoice' - $ref: '#/components/schemas/FallbackNeuphonicVoice' - $ref: '#/components/schemas/FallbackSesameVoice' - $ref: '#/components/schemas/FallbackInworldVoice' title: FallbackPlanVoicesItems FallbackPlan: type: object properties: voices: type: array items: $ref: '#/components/schemas/FallbackPlanVoicesItems' description: >- This is the list of voices to fallback to in the event that the primary voice provider fails. required: - voices title: FallbackPlan AzureVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/AzureVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/AzureVoiceId' description: This is the provider-specific ID that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. speed: type: number format: double description: This is the speed multiplier that will be used. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: AzureVoice CartesiaVoiceProvider: type: string enum: - cartesia description: This is the voice provider that will be used. title: CartesiaVoiceProvider CartesiaVoiceModel: type: string enum: - sonic-3 - sonic-3-2026-01-12 - sonic-3-2025-10-27 - sonic-2 - sonic-2-2025-06-11 - sonic-english - sonic-multilingual - sonic-preview - sonic description: >- This is the model that will be used. This is optional and will default to the correct model for the voiceId. title: CartesiaVoiceModel CartesiaVoiceLanguage: type: string enum: - ar - bg - bn - cs - da - de - el - en - es - fi - fr - gu - he - hi - hr - hu - id - it - ja - ka - kn - ko - ml - mr - ms - nl - 'no' - pa - pl - pt - ro - ru - sk - sv - ta - te - th - tl - tr - uk - vi - zh description: >- This is the language that will be used. This is optional and will default to the correct language for the voiceId. title: CartesiaVoiceLanguage CartesiaVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/CartesiaVoiceProvider' description: This is the voice provider that will be used. voiceId: type: string description: The ID of the particular voice you want to use. model: $ref: '#/components/schemas/CartesiaVoiceModel' description: >- This is the model that will be used. This is optional and will default to the correct model for the voiceId. language: $ref: '#/components/schemas/CartesiaVoiceLanguage' description: >- This is the language that will be used. This is optional and will default to the correct language for the voiceId. experimentalControls: $ref: '#/components/schemas/CartesiaExperimentalControls' description: Experimental controls for Cartesia voice generation generationConfig: $ref: '#/components/schemas/CartesiaGenerationConfig' description: >- Generation config for fine-grained control of sonic-3 voice output (speed, volume, and experimental controls). Only available for sonic-3 model. pronunciationDictId: type: string description: >- Pronunciation dictionary ID for sonic-3. Allows custom pronunciations for specific words. Only available for sonic-3 model. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: CartesiaVoice CustomVoiceProvider: type: string enum: - custom-voice description: >- This is the voice provider that will be used. Use `custom-voice` for providers that are not natively supported. title: CustomVoiceProvider CustomVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/CustomVoiceProvider' description: >- This is the voice provider that will be used. Use `custom-voice` for providers that are not natively supported. voiceId: type: string description: >- This is the provider-specific ID that will be used. This is passed in the voice request payload to identify the voice to use. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. server: $ref: '#/components/schemas/Server' description: >- This is where the voice request will be sent. Request Example: POST https://{server.url} Content-Type: application/json { "message": { "type": "voice-request", "text": "Hello, world!", "sampleRate": 24000, ...other metadata about the call... } } Response Expected: 1-channel 16-bit raw PCM audio at the sample rate specified in the request. Here is how the response will be piped to the transport: ``` response.on('data', (chunk: Buffer) => { outputStream.write(chunk); }); ``` fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - server title: CustomVoice DeepgramVoiceProvider: type: string enum: - deepgram description: This is the voice provider that will be used. title: DeepgramVoiceProvider DeepgramVoiceId: type: string enum: - asteria - luna - stella - athena - hera - orion - arcas - perseus - angus - orpheus - helios - zeus - thalia - andromeda - helena - apollo - arcas - aries - amalthea - asteria - athena - atlas - aurora - callista - cora - cordelia - delia - draco - electra - harmonia - hera - hermes - hyperion - iris - janus - juno - jupiter - luna - mars - minerva - neptune - odysseus - ophelia - orion - orpheus - pandora - phoebe - pluto - saturn - selene - theia - vesta - zeus - celeste - estrella - nestor - sirio - carina - alvaro - diana - aquila - selena - javier description: This is the provider-specific ID that will be used. title: DeepgramVoiceId DeepgramVoiceModel: type: string enum: - aura - aura-2 description: >- This is the model that will be used. Defaults to 'aura-2' when not specified. title: DeepgramVoiceModel DeepgramVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/DeepgramVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/DeepgramVoiceId' description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/DeepgramVoiceModel' description: >- This is the model that will be used. Defaults to 'aura-2' when not specified. mipOptOut: type: boolean default: false description: >- If set to true, this will add mip_opt_out=true as a query parameter of all API requests. See https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program#want-to-opt-out This will only be used if you are using your own Deepgram API key. @default false chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: DeepgramVoice ElevenLabsVoiceId0: type: string enum: - burt - marissa - andrea - sarah - phillip - steve - joseph - myra - paula - ryan - drew - paul - mrb - matilda - mark title: ElevenLabsVoiceId0 ElevenLabsVoiceId: oneOf: - $ref: '#/components/schemas/ElevenLabsVoiceId0' - type: string description: >- This is the provider-specific ID that will be used. Ensure the Voice is present in your 11Labs Voice Library. title: ElevenLabsVoiceId ElevenLabsVoiceModel: type: string enum: - eleven_multilingual_v2 - eleven_turbo_v2 - eleven_turbo_v2_5 - eleven_flash_v2 - eleven_flash_v2_5 - eleven_monolingual_v1 - eleven_v3 description: >- This is the model that will be used. Defaults to 'eleven_turbo_v2' if not specified. title: ElevenLabsVoiceModel ElevenLabsVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: type: string enum: - 11labs description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/ElevenLabsVoiceId' description: >- This is the provider-specific ID that will be used. Ensure the Voice is present in your 11Labs Voice Library. stability: type: number format: double description: Defines the stability for voice settings. similarityBoost: type: number format: double description: Defines the similarity boost for voice settings. style: type: number format: double description: Defines the style for voice settings. useSpeakerBoost: type: boolean description: Defines the use speaker boost for voice settings. speed: type: number format: double description: Defines the speed for voice settings. optimizeStreamingLatency: type: number format: double description: >- Defines the optimize streaming latency for voice settings. Defaults to 3. enableSsmlParsing: type: boolean description: >- This enables the use of https://elevenlabs.io/docs/speech-synthesis/prompting#pronunciation. Defaults to false to save latency. @default false autoMode: type: boolean description: Defines the auto mode for voice settings. Defaults to false. model: $ref: '#/components/schemas/ElevenLabsVoiceModel' description: >- This is the model that will be used. Defaults to 'eleven_turbo_v2' if not specified. language: type: string description: >- This is the language (ISO 639-1) that is enforced for the model. Currently only Turbo v2.5 supports language enforcement. For other models, an error will be returned if language code is provided. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. pronunciationDictionaryLocators: type: array items: $ref: '#/components/schemas/ElevenLabsPronunciationDictionaryLocator' description: This is the pronunciation dictionary locators to use. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: ElevenLabsVoice HumeVoiceProvider: type: string enum: - hume description: This is the voice provider that will be used. title: HumeVoiceProvider HumeVoiceModel: type: string enum: - octave - octave2 description: This is the model that will be used. title: HumeVoiceModel HumeVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/HumeVoiceProvider' description: This is the voice provider that will be used. model: $ref: '#/components/schemas/HumeVoiceModel' description: This is the model that will be used. voiceId: type: string description: The ID of the particular voice you want to use. isCustomHumeVoice: type: boolean description: >- Indicates whether the chosen voice is a preset Hume AI voice or a custom voice. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. description: type: string description: >- Natural language instructions describing how the synthesized speech should sound, including but not limited to tone, intonation, pacing, and accent (e.g., 'a soft, gentle voice with a strong British accent'). If a Voice is specified in the request, this description serves as acting instructions. If no Voice is specified, a new voice is generated based on this description. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: HumeVoice LmntVoiceProvider: type: string enum: - lmnt description: This is the voice provider that will be used. title: LmntVoiceProvider LmntVoiceId0: type: string enum: - amy - ansel - autumn - ava - brandon - caleb - cassian - chloe - dalton - daniel - dustin - elowen - evander - huxley - james - juniper - kennedy - lauren - leah - lily - lucas - magnus - miles - morgan - natalie - nathan - noah - nyssa - oliver - paige - ryan - sadie - sophie - stella - terrence - tyler - vesper - violet - warrick - zain - zeke - zoe title: LmntVoiceId0 LMNTVoiceId: oneOf: - $ref: '#/components/schemas/LmntVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: LMNTVoiceId LmntVoiceLanguage: type: string enum: - aa - ab - ae - af - ak - am - an - ar - as - av - ay - az - ba - be - bg - bh - bi - bm - bn - bo - br - bs - ca - ce - ch - co - cr - cs - cu - cv - cy - da - de - dv - dz - ee - el - en - eo - es - et - eu - fa - ff - fi - fj - fo - fr - fy - ga - gd - gl - gn - gu - gv - ha - he - hi - ho - hr - ht - hu - hy - hz - ia - id - ie - ig - ii - ik - io - is - it - iu - ja - jv - ka - kg - ki - kj - kk - kl - km - kn - ko - kr - ks - ku - kv - kw - ky - la - lb - lg - li - ln - lo - lt - lu - lv - mg - mh - mi - mk - ml - mn - mr - ms - mt - my - na - nb - nd - ne - ng - nl - nn - 'no' - nr - nv - ny - oc - oj - om - or - os - pa - pi - pl - ps - pt - qu - rm - rn - ro - ru - rw - sa - sc - sd - se - sg - si - sk - sl - sm - sn - so - sq - sr - ss - st - su - sv - sw - ta - te - tg - th - ti - tk - tl - tn - to - tr - ts - tt - tw - ty - ug - uk - ur - uz - ve - vi - vo - wa - wo - xh - yi - yue - yo - za - zh - zu - auto description: Two letter ISO 639-1 language code. Use "auto" for auto-detection. title: LmntVoiceLanguage LMNTVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/LmntVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/LMNTVoiceId' description: This is the provider-specific ID that will be used. speed: type: number format: double description: This is the speed multiplier that will be used. language: $ref: '#/components/schemas/LmntVoiceLanguage' description: Two letter ISO 639-1 language code. Use "auto" for auto-detection. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: LMNTVoice NeuphonicVoiceProvider: type: string enum: - neuphonic description: This is the voice provider that will be used. title: NeuphonicVoiceProvider NeuphonicVoiceModel: type: string enum: - neu_hq - neu_fast description: >- This is the model that will be used. Defaults to 'neu_fast' if not specified. title: NeuphonicVoiceModel NeuphonicVoiceLanguage: type: object properties: {} description: This is the language (ISO 639-1) that is enforced for the model. title: NeuphonicVoiceLanguage NeuphonicVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/NeuphonicVoiceProvider' description: This is the voice provider that will be used. voiceId: type: string description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/NeuphonicVoiceModel' description: >- This is the model that will be used. Defaults to 'neu_fast' if not specified. language: $ref: '#/components/schemas/NeuphonicVoiceLanguage' description: This is the language (ISO 639-1) that is enforced for the model. speed: type: number format: double description: This is the speed multiplier that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId - language title: NeuphonicVoice OpenAiVoiceProvider: type: string enum: - openai description: This is the voice provider that will be used. title: OpenAiVoiceProvider OpenAiVoiceId0: type: string enum: - alloy - echo - fable - onyx - nova - shimmer - marin - cedar title: OpenAiVoiceId0 OpenAIVoiceId: oneOf: - $ref: '#/components/schemas/OpenAiVoiceId0' - type: string description: >- This is the provider-specific ID that will be used. Please note that ash, ballad, coral, sage, and verse may only be used with realtime models. title: OpenAIVoiceId OpenAiVoiceModel: type: string enum: - tts-1 - tts-1-hd - gpt-4o-mini-tts description: This is the model that will be used for text-to-speech. title: OpenAiVoiceModel OpenAIVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/OpenAiVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/OpenAIVoiceId' description: >- This is the provider-specific ID that will be used. Please note that ash, ballad, coral, sage, and verse may only be used with realtime models. model: $ref: '#/components/schemas/OpenAiVoiceModel' description: This is the model that will be used for text-to-speech. instructions: type: string description: >- This is a prompt that allows you to control the voice of your generated audio. Does not work with 'tts-1' or 'tts-1-hd' models. speed: type: number format: double description: This is the speed multiplier that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: OpenAIVoice PlayHtVoiceProvider: type: string enum: - playht description: This is the voice provider that will be used. title: PlayHtVoiceProvider PlayHtVoiceId0: type: string enum: - jennifer - melissa - will - chris - matt - jack - ruby - davis - donna - michael title: PlayHtVoiceId0 PlayHTVoiceId: oneOf: - $ref: '#/components/schemas/PlayHtVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: PlayHTVoiceId PlayHtVoiceEmotion: type: string enum: - female_happy - female_sad - female_angry - female_fearful - female_disgust - female_surprised - male_happy - male_sad - male_angry - male_fearful - male_disgust - male_surprised description: An emotion to be applied to the speech. title: PlayHtVoiceEmotion PlayHtVoiceModel: type: string enum: - PlayHT2.0 - PlayHT2.0-turbo - Play3.0-mini - PlayDialog description: Playht voice model/engine to use. title: PlayHtVoiceModel PlayHtVoiceLanguage: type: string enum: - afrikaans - albanian - amharic - arabic - bengali - bulgarian - catalan - croatian - czech - danish - dutch - english - french - galician - german - greek - hebrew - hindi - hungarian - indonesian - italian - japanese - korean - malay - mandarin - polish - portuguese - russian - serbian - spanish - swedish - tagalog - thai - turkish - ukrainian - urdu - xhosa description: The language to use for the speech. title: PlayHtVoiceLanguage PlayHTVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/PlayHtVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/PlayHTVoiceId' description: This is the provider-specific ID that will be used. speed: type: number format: double description: This is the speed multiplier that will be used. temperature: type: number format: double description: >- A floating point number between 0, exclusive, and 2, inclusive. If equal to null or not provided, the model's default temperature will be used. The temperature parameter controls variance. Lower temperatures result in more predictable results, higher temperatures allow each run to vary more, so the voice may sound less like the baseline voice. emotion: $ref: '#/components/schemas/PlayHtVoiceEmotion' description: An emotion to be applied to the speech. voiceGuidance: type: number format: double description: >- A number between 1 and 6. Use lower numbers to reduce how unique your chosen voice will be compared to other voices. styleGuidance: type: number format: double description: >- A number between 1 and 30. Use lower numbers to to reduce how strong your chosen emotion will be. Higher numbers will create a very emotional performance. textGuidance: type: number format: double description: >- A number between 1 and 2. This number influences how closely the generated speech adheres to the input text. Use lower values to create more fluid speech, but with a higher chance of deviating from the input text. Higher numbers will make the generated speech more accurate to the input text, ensuring that the words spoken align closely with the provided text. model: $ref: '#/components/schemas/PlayHtVoiceModel' description: Playht voice model/engine to use. language: $ref: '#/components/schemas/PlayHtVoiceLanguage' description: The language to use for the speech. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: PlayHTVoice WellSaidVoiceProvider: type: string enum: - wellsaid description: This is the voice provider that will be used. title: WellSaidVoiceProvider WellSaidVoiceModel: type: string enum: - caruso - legacy description: This is the model that will be used. title: WellSaidVoiceModel WellSaidVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/WellSaidVoiceProvider' description: This is the voice provider that will be used. voiceId: type: string description: The WellSaid speaker ID to synthesize. model: $ref: '#/components/schemas/WellSaidVoiceModel' description: This is the model that will be used. enableSsml: type: boolean description: Enables limited SSML translation for input text. libraryIds: type: array items: type: string description: Array of library IDs to use for voice synthesis. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: WellSaidVoice RimeAiVoiceProvider: type: string enum: - rime-ai description: This is the voice provider that will be used. title: RimeAiVoiceProvider RimeAiVoiceId0: type: string enum: - cove - moon - wildflower - eva - amber - maya - lagoon - breeze - helen - joy - marsh - creek - cedar - alpine - summit - nicholas - tyler - colin - hank - thunder - astra - eucalyptus - moraine - peak - tundra - mesa_extra - talon - marlu - glacier - falcon - luna - celeste - estelle - andromeda - esther - lyra - lintel - oculus - vespera - transom - bond - arcade - atrium - cupola - fern - sirius - orion - masonry - albion - parapet description: >- Popular Rime AI voices across mist, mistv2, and arcana models. Any valid Rime AI voice ID is accepted, not just these suggestions. title: RimeAiVoiceId0 RimeAIVoiceId: oneOf: - $ref: '#/components/schemas/RimeAiVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: RimeAIVoiceId RimeAiVoiceModel: type: string enum: - arcana - mistv2 - mist description: >- This is the model that will be used. Defaults to 'arcana' when not specified. title: RimeAiVoiceModel RimeAiVoiceLanguage: type: string enum: - en - es - de - fr - ar - hi - ja - he - pt - ta - si description: >- Language for speech synthesis. Uses ISO 639 codes. Supported: en, es, de, fr, ar, hi, ja, he, pt, ta, si. title: RimeAiVoiceLanguage RimeAIVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/RimeAiVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/RimeAIVoiceId' description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/RimeAiVoiceModel' description: >- This is the model that will be used. Defaults to 'arcana' when not specified. speed: type: number format: double description: This is the speed multiplier that will be used. pauseBetweenBrackets: type: boolean description: >- This is a flag that controls whether to add slight pauses using angle brackets. Example: "Hi. <200> I'd love to have a conversation with you." adds a 200ms pause between the first and second sentences. phonemizeBetweenBrackets: type: boolean description: >- This is a flag that controls whether text inside brackets should be phonemized (converted to phonetic pronunciation) - Example: "{h'El.o} World" will pronounce "Hello" as expected. reduceLatency: type: boolean description: >- This is a flag that controls whether to optimize for reduced latency in streaming. https://docs.rime.ai/api-reference/endpoint/websockets#param-reduce-latency inlineSpeedAlpha: type: string description: >- This is a string that allows inline speed control using alpha notation. https://docs.rime.ai/api-reference/endpoint/websockets#param-inline-speed-alpha language: $ref: '#/components/schemas/RimeAiVoiceLanguage' description: >- Language for speech synthesis. Uses ISO 639 codes. Supported: en, es, de, fr, ar, hi, ja, he, pt, ta, si. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: RimeAIVoice SmallestAiVoiceProvider: type: string enum: - smallest-ai description: This is the voice provider that will be used. title: SmallestAiVoiceProvider SmallestAiVoiceId0: type: string enum: - emily - jasmine - arman - james - mithali - aravind - raj - diya - raman - ananya - isha - william - aarav - monika - niharika - deepika - raghav - kajal - radhika - mansi - nisha - saurabh - pooja - saina - sanya title: SmallestAiVoiceId0 SmallestAIVoiceId: oneOf: - $ref: '#/components/schemas/SmallestAiVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: SmallestAIVoiceId SmallestAiVoiceModel: type: string enum: - lightning description: >- Smallest AI voice model to use. Defaults to 'lightning' when not specified. title: SmallestAiVoiceModel SmallestAIVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/SmallestAiVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/SmallestAIVoiceId' description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/SmallestAiVoiceModel' description: >- Smallest AI voice model to use. Defaults to 'lightning' when not specified. speed: type: number format: double description: This is the speed multiplier that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: SmallestAIVoice TavusVoiceProvider: type: string enum: - tavus description: This is the voice provider that will be used. title: TavusVoiceProvider TavusVoiceVoiceId0: type: string enum: - r52da2535a title: TavusVoiceVoiceId0 TavusVoiceVoiceId: oneOf: - $ref: '#/components/schemas/TavusVoiceVoiceId0' - type: string description: This is the provider-specific ID that will be used. title: TavusVoiceVoiceId TavusVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/TavusVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/TavusVoiceVoiceId' description: This is the provider-specific ID that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. personaId: type: string description: >- This is the unique identifier for the persona that the replica will use in the conversation. callbackUrl: type: string description: >- This is the url that will receive webhooks with updates regarding the conversation state. conversationName: type: string description: This is the name for the conversation. conversationalContext: type: string description: >- This is the context that will be appended to any context provided in the persona, if one is provided. customGreeting: type: string description: >- This is the custom greeting that the replica will give once a participant joines the conversation. properties: $ref: '#/components/schemas/TavusConversationProperties' description: These are optional properties used to customize the conversation. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: TavusVoice VapiVoiceProvider: type: string enum: - vapi description: This is the voice provider that will be used. title: VapiVoiceProvider VapiVoiceVoiceId: type: string enum: - Clara - Godfrey - Layla - Sid - Gustavo - Elliot - Kylie - Rohan - Lily - Savannah - Hana - Neha - Cole - Harry - Paige - Spencer - Nico - Kai - Emma - Sagar - Neil - Naina - Leah - Tara - Jess - Leo - Dan - Mia - Zac - Zoe description: The voices provided by Vapi title: VapiVoiceVoiceId VapiVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/VapiVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/VapiVoiceVoiceId' description: The voices provided by Vapi speed: type: number format: double default: 1 description: |- This is the speed multiplier that will be used. @default 1 pronunciationDictionary: type: array items: $ref: '#/components/schemas/VapiPronunciationDictionaryLocator' description: >- List of pronunciation dictionary locators for custom word pronunciations. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: VapiVoice SesameVoiceProvider: type: string enum: - sesame description: This is the voice provider that will be used. title: SesameVoiceProvider SesameVoiceModel: type: string enum: - csm-1b description: This is the model that will be used. title: SesameVoiceModel SesameVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/SesameVoiceProvider' description: This is the voice provider that will be used. voiceId: type: string description: This is the provider-specific ID that will be used. model: $ref: '#/components/schemas/SesameVoiceModel' description: This is the model that will be used. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId - model title: SesameVoice InworldVoiceProvider: type: string enum: - inworld description: This is the voice provider that will be used. title: InworldVoiceProvider InworldVoiceVoiceId: type: string enum: - Alex - Ashley - Craig - Deborah - Dennis - Edward - Elizabeth - Hades - Julia - Pixie - Mark - Olivia - Priya - Ronald - Sarah - Shaun - Theodore - Timothy - Wendy - Dominus - Hana - Clive - Carter - Blake - Luna - Yichen - Xiaoyin - Xinyi - Jing - Erik - Katrien - Lennart - Lore - Alain - Hélène - Mathieu - Étienne - Johanna - Josef - Gianni - Orietta - Asuka - Satoshi - Hyunwoo - Minji - Seojun - Yoona - Szymon - Wojciech - Heitor - Maitê - Diego - Lupita - Miguel - Rafael - Svetlana - Elena - Dmitry - Nikolai - Riya - Manoj - Yael - Oren - Nour - Omar description: >- Available voices by language: • en: Alex, Ashley, Craig, Deborah, Dennis, Edward, Elizabeth, Hades, Julia, Pixie, Mark, Olivia, Priya, Ronald, Sarah, Shaun, Theodore, Timothy, Wendy, Dominus, Hana, Clive, Carter, Blake, Luna • zh: Yichen, Xiaoyin, Xinyi, Jing • nl: Erik, Katrien, Lennart, Lore • fr: Alain, Hélène, Mathieu, Étienne • de: Johanna, Josef • it: Gianni, Orietta • ja: Asuka, Satoshi • ko: Hyunwoo, Minji, Seojun, Yoona • pl: Szymon, Wojciech • pt: Heitor, Maitê • es: Diego, Lupita, Miguel, Rafael • ru: Svetlana, Elena, Dmitry, Nikolai • hi: Riya, Manoj • he: Yael, Oren • ar: Nour, Omar title: InworldVoiceVoiceId InworldVoiceModel: type: string enum: - inworld-tts-1 default: inworld-tts-1 description: This is the model that will be used. title: InworldVoiceModel InworldVoiceLanguageCode: type: string enum: - en - zh - ko - nl - fr - es - ja - de - it - pl - pt - ru - hi - he - ar default: en description: Language code for Inworld TTS synthesis title: InworldVoiceLanguageCode InworldVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/InworldVoiceProvider' description: This is the voice provider that will be used. voiceId: $ref: '#/components/schemas/InworldVoiceVoiceId' description: >- Available voices by language: • en: Alex, Ashley, Craig, Deborah, Dennis, Edward, Elizabeth, Hades, Julia, Pixie, Mark, Olivia, Priya, Ronald, Sarah, Shaun, Theodore, Timothy, Wendy, Dominus, Hana, Clive, Carter, Blake, Luna • zh: Yichen, Xiaoyin, Xinyi, Jing • nl: Erik, Katrien, Lennart, Lore • fr: Alain, Hélène, Mathieu, Étienne • de: Johanna, Josef • it: Gianni, Orietta • ja: Asuka, Satoshi • ko: Hyunwoo, Minji, Seojun, Yoona • pl: Szymon, Wojciech • pt: Heitor, Maitê • es: Diego, Lupita, Miguel, Rafael • ru: Svetlana, Elena, Dmitry, Nikolai • hi: Riya, Manoj • he: Yael, Oren • ar: Nour, Omar model: $ref: '#/components/schemas/InworldVoiceModel' description: This is the model that will be used. languageCode: $ref: '#/components/schemas/InworldVoiceLanguageCode' description: Language code for Inworld TTS synthesis temperature: type: number format: double default: 1.1 description: >- A floating point number between 0, exclusive, and 2, inclusive. If equal to null or not provided, the model's default temperature of 1.1 will be used. The temperature parameter controls variance. Higher values will make the output more random and can lead to more expressive results. Lower values will make it more deterministic. See https://docs.inworld.ai/docs/tts/capabilities/generating-audio#additional-configurations for more details. speakingRate: type: number format: double default: 1 description: >- A floating point number between 0.5, inclusive, and 1.5, inclusive. If equal to null or not provided, the model's default speaking speed of 1.0 will be used. Values above 0.8 are recommended for higher quality. See https://docs.inworld.ai/docs/tts/capabilities/generating-audio#additional-configurations for more details. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: InworldVoice MinimaxVoiceProvider: type: string enum: - minimax description: This is the voice provider that will be used. title: MinimaxVoiceProvider MinimaxVoiceModel: type: string enum: - speech-02-hd - speech-02-turbo - speech-2.5-turbo-preview default: speech-02-turbo description: >- This is the model that will be used. Options are 'speech-02-hd' and 'speech-02-turbo'. speech-02-hd is optimized for high-fidelity applications like voiceovers and audiobooks. speech-02-turbo is designed for real-time applications with low latency. @default "speech-02-turbo" title: MinimaxVoiceModel MinimaxVoiceSubtitleType: type: string enum: - word - sentence default: sentence description: |- Controls the granularity of subtitle/timing data returned by Minimax during synthesis. Set to 'word' to receive per-word timestamps in assistant.speechStarted events for karaoke-style caption rendering. @default "sentence" title: MinimaxVoiceSubtitleType MinimaxVoiceRegion: type: string enum: - worldwide - china default: worldwide description: The region for Minimax API. Defaults to "worldwide". title: MinimaxVoiceRegion MinimaxVoiceLanguageBoost: type: string enum: - Chinese - Chinese,Yue - English - Arabic - Russian - Spanish - French - Portuguese - German - Turkish - Dutch - Ukrainian - Vietnamese - Indonesian - Japanese - Italian - Korean - Thai - Polish - Romanian - Greek - Czech - Finnish - Hindi - Bulgarian - Danish - Hebrew - Malay - Persian - Slovak - Swedish - Croatian - Filipino - Hungarian - Norwegian - Slovenian - Catalan - Nynorsk - Tamil - Afrikaans - auto description: >- Language hint for MiniMax T2A. Example: yue (Cantonese), zh (Chinese), en (English). title: MinimaxVoiceLanguageBoost MinimaxVoice: type: object properties: cachingEnabled: type: boolean default: true description: This is the flag to toggle voice caching for the assistant. provider: $ref: '#/components/schemas/MinimaxVoiceProvider' description: This is the voice provider that will be used. voiceId: type: string description: >- This is the provider-specific ID that will be used. Use a voice from MINIMAX_PREDEFINED_VOICES or a custom cloned voice ID. model: $ref: '#/components/schemas/MinimaxVoiceModel' description: >- This is the model that will be used. Options are 'speech-02-hd' and 'speech-02-turbo'. speech-02-hd is optimized for high-fidelity applications like voiceovers and audiobooks. speech-02-turbo is designed for real-time applications with low latency. @default "speech-02-turbo" emotion: type: string description: >- The emotion to use for the voice. If not provided, will use auto-detect mode. Options include: 'happy', 'sad', 'angry', 'fearful', 'surprised', 'disgusted', 'neutral' subtitleType: $ref: '#/components/schemas/MinimaxVoiceSubtitleType' description: |- Controls the granularity of subtitle/timing data returned by Minimax during synthesis. Set to 'word' to receive per-word timestamps in assistant.speechStarted events for karaoke-style caption rendering. @default "sentence" pitch: type: number format: double default: 0 description: |- Voice pitch adjustment. Range from -12 to 12 semitones. @default 0 speed: type: number format: double default: 1 description: |- Voice speed adjustment. Range from 0.5 to 2.0. @default 1.0 volume: type: number format: double default: 1 description: |- Voice volume adjustment. Range from 0.5 to 2.0. @default 1.0 region: $ref: '#/components/schemas/MinimaxVoiceRegion' description: The region for Minimax API. Defaults to "worldwide". languageBoost: $ref: '#/components/schemas/MinimaxVoiceLanguageBoost' description: >- Language hint for MiniMax T2A. Example: yue (Cantonese), zh (Chinese), en (English). textNormalizationEnabled: type: boolean default: true description: >- Enable MiniMax text normalization to improve number reading and formatting. chunkPlan: $ref: '#/components/schemas/ChunkPlan' description: >- This is the plan for chunking the model output before it is sent to the voice provider. fallbackPlan: $ref: '#/components/schemas/FallbackPlan' description: >- This is the plan for voice provider fallbacks in the event that the primary voice provider fails. required: - provider - voiceId title: MinimaxVoice AssistantOverridesVoice: oneOf: - $ref: '#/components/schemas/AzureVoice' - $ref: '#/components/schemas/CartesiaVoice' - $ref: '#/components/schemas/CustomVoice' - $ref: '#/components/schemas/DeepgramVoice' - $ref: '#/components/schemas/ElevenLabsVoice' - $ref: '#/components/schemas/HumeVoice' - $ref: '#/components/schemas/LMNTVoice' - $ref: '#/components/schemas/NeuphonicVoice' - $ref: '#/components/schemas/OpenAIVoice' - $ref: '#/components/schemas/PlayHTVoice' - $ref: '#/components/schemas/WellSaidVoice' - $ref: '#/components/schemas/RimeAIVoice' - $ref: '#/components/schemas/SmallestAIVoice' - $ref: '#/components/schemas/TavusVoice' - $ref: '#/components/schemas/VapiVoice' - $ref: '#/components/schemas/SesameVoice' - $ref: '#/components/schemas/InworldVoice' - $ref: '#/components/schemas/MinimaxVoice' description: These are the options for the assistant's voice. title: AssistantOverridesVoice AssistantOverridesFirstMessageMode: type: string enum: - assistant-speaks-first - assistant-speaks-first-with-model-generated-message - assistant-waits-for-user description: >- This is the mode for the first message. Default is 'assistant-speaks-first'. Use: - 'assistant-speaks-first' to have the assistant speak first. - 'assistant-waits-for-user' to have the assistant wait for the user to speak first. - 'assistant-speaks-first-with-model-generated-message' to have the assistant speak first with a message generated by the model based on the conversation state. (`assistant.model.messages` at call start, `call.messages` at squad transfer points). @default 'assistant-speaks-first' title: AssistantOverridesFirstMessageMode AssistantOverridesVoicemailDetection0: type: string enum: - 'off' title: AssistantOverridesVoicemailDetection0 GoogleVoicemailDetectionPlanProvider: type: string enum: - google description: This is the provider to use for voicemail detection. title: GoogleVoicemailDetectionPlanProvider VoicemailDetectionBackoffPlan: type: object properties: startAtSeconds: type: number format: double default: 5 description: >- This is the number of seconds to wait before starting the first retry attempt. frequencySeconds: type: number format: double default: 5 description: This is the interval in seconds between retry attempts. maxRetries: type: number format: double default: 6 description: This is the maximum number of retry attempts before giving up. title: VoicemailDetectionBackoffPlan GoogleVoicemailDetectionPlanType: type: string enum: - audio - transcript description: |- This is the detection type to use for voicemail detection. - 'audio': Uses native audio models (default) - 'transcript': Uses ASR/transcript-based detection @default 'audio' (audio detection) title: GoogleVoicemailDetectionPlanType GoogleVoicemailDetectionPlan: type: object properties: beepMaxAwaitSeconds: type: number format: double default: 30 description: >- This is the maximum duration from the start of the call that we will wait for a voicemail beep, before speaking our message - If we detect a voicemail beep before this, we will speak the message at that point. - Setting too low a value means that the bot will start speaking its voicemail message too early. If it does so before the actual beep, it will get cut off. You should definitely tune this to your use case. @default 30 @min 0 @max 60 provider: $ref: '#/components/schemas/GoogleVoicemailDetectionPlanProvider' description: This is the provider to use for voicemail detection. backoffPlan: $ref: '#/components/schemas/VoicemailDetectionBackoffPlan' description: This is the backoff plan for the voicemail detection. type: $ref: '#/components/schemas/GoogleVoicemailDetectionPlanType' description: |- This is the detection type to use for voicemail detection. - 'audio': Uses native audio models (default) - 'transcript': Uses ASR/transcript-based detection @default 'audio' (audio detection) required: - provider title: GoogleVoicemailDetectionPlan OpenAiVoicemailDetectionPlanProvider: type: string enum: - openai description: This is the provider to use for voicemail detection. title: OpenAiVoicemailDetectionPlanProvider OpenAiVoicemailDetectionPlanType: type: string enum: - audio - transcript description: |- This is the detection type to use for voicemail detection. - 'audio': Uses native audio models (default) - 'transcript': Uses ASR/transcript-based detection @default 'audio' (audio detection) title: OpenAiVoicemailDetectionPlanType OpenAIVoicemailDetectionPlan: type: object properties: beepMaxAwaitSeconds: type: number format: double default: 30 description: >- This is the maximum duration from the start of the call that we will wait for a voicemail beep, before speaking our message - If we detect a voicemail beep before this, we will speak the message at that point. - Setting too low a value means that the bot will start speaking its voicemail message too early. If it does so before the actual beep, it will get cut off. You should definitely tune this to your use case. @default 30 @min 0 @max 60 provider: $ref: '#/components/schemas/OpenAiVoicemailDetectionPlanProvider' description: This is the provider to use for voicemail detection. backoffPlan: $ref: '#/components/schemas/VoicemailDetectionBackoffPlan' description: This is the backoff plan for the voicemail detection. type: $ref: '#/components/schemas/OpenAiVoicemailDetectionPlanType' description: |- This is the detection type to use for voicemail detection. - 'audio': Uses native audio models (default) - 'transcript': Uses ASR/transcript-based detection @default 'audio' (audio detection) required: - provider title: OpenAIVoicemailDetectionPlan TwilioVoicemailDetectionPlanProvider: type: string enum: - twilio description: This is the provider to use for voicemail detection. title: TwilioVoicemailDetectionPlanProvider TwilioVoicemailDetectionPlanVoicemailDetectionTypes: type: string enum: - machine_start - human - fax - unknown - machine_end_beep - machine_end_silence - machine_end_other description: >- These are the AMD messages from Twilio that are considered as voicemail. Default is ['machine_end_beep', 'machine_end_silence']. @default {Array} ['machine_end_beep', 'machine_end_silence'] title: TwilioVoicemailDetectionPlanVoicemailDetectionTypes TwilioVoicemailDetectionPlan: type: object properties: provider: $ref: '#/components/schemas/TwilioVoicemailDetectionPlanProvider' description: This is the provider to use for voicemail detection. voicemailDetectionTypes: $ref: >- #/components/schemas/TwilioVoicemailDetectionPlanVoicemailDetectionTypes description: >- These are the AMD messages from Twilio that are considered as voicemail. Default is ['machine_end_beep', 'machine_end_silence']. @default {Array} ['machine_end_beep', 'machine_end_silence'] enabled: type: boolean description: >- This sets whether the assistant should detect voicemail. Defaults to true. @default true machineDetectionTimeout: type: number format: double description: >- The number of seconds that Twilio should attempt to perform answering machine detection before timing out and returning AnsweredBy as unknown. Default is 30 seconds. Increasing this value will provide the engine more time to make a determination. This can be useful when DetectMessageEnd is provided in the MachineDetection parameter and there is an expectation of long answering machine greetings that can exceed 30 seconds. Decreasing this value will reduce the amount of time the engine has to make a determination. This can be particularly useful when the Enable option is provided in the MachineDetection parameter and you want to limit the time for initial detection. Check the [Twilio docs](https://www.twilio.com/docs/voice/answering-machine-detection#optional-api-tuning-parameters) for more info. @default 30 machineDetectionSpeechThreshold: type: number format: double description: >- The number of milliseconds that is used as the measuring stick for the length of the speech activity. Durations lower than this value will be interpreted as a human, longer as a machine. Default is 2400 milliseconds. Increasing this value will reduce the chance of a False Machine (detected machine, actually human) for a long human greeting (e.g., a business greeting) but increase the time it takes to detect a machine. Decreasing this value will reduce the chances of a False Human (detected human, actually machine) for short voicemail greetings. The value of this parameter may need to be reduced by more than 1000ms to detect very short voicemail greetings. A reduction of that significance can result in increased False Machine detections. Adjusting the MachineDetectionSpeechEndThreshold is likely the better approach for short voicemails. Decreasing MachineDetectionSpeechThreshold will also reduce the time it takes to detect a machine. Check the [Twilio docs](https://www.twilio.com/docs/voice/answering-machine-detection#optional-api-tuning-parameters) for more info. @default 2400 machineDetectionSpeechEndThreshold: type: number format: double description: >- The number of milliseconds of silence after speech activity at which point the speech activity is considered complete. Default is 1200 milliseconds. Increasing this value will typically be used to better address the short voicemail greeting scenarios. For short voicemails, there is typically 1000-2000ms of audio followed by 1200-2400ms of silence and then additional audio before the beep. Increasing the MachineDetectionSpeechEndThreshold to ~2500ms will treat the 1200-2400ms of silence as a gap in the greeting but not the end of the greeting and will result in a machine detection. The downsides of such a change include: - Increasing the delay for human detection by the amount you increase this parameter, e.g., a change of 1200ms to 2500ms increases human detection delay by 1300ms. - Cases where a human has two utterances separated by a period of silence (e.g. a "Hello", then 2000ms of silence, and another "Hello") may be interpreted as a machine. Decreasing this value will result in faster human detection. The consequence is that it can lead to increased False Human (detected human, actually machine) detections because a silence gap in a voicemail greeting (not necessarily just in short voicemail scenarios) can be incorrectly interpreted as the end of speech. Check the [Twilio docs](https://www.twilio.com/docs/voice/answering-machine-detection#optional-api-tuning-parameters) for more info. @default 1200 machineDetectionSilenceTimeout: type: number format: double description: >- The number of milliseconds of initial silence after which an unknown AnsweredBy result will be returned. Default is 5000 milliseconds. Increasing this value will result in waiting for a longer period of initial silence before returning an 'unknown' AMD result. Decreasing this value will result in waiting for a shorter period of initial silence before returning an 'unknown' AMD result. Check the [Twilio docs](https://www.twilio.com/docs/voice/answering-machine-detection#optional-api-tuning-parameters) for more info. @default 5000 required: - provider title: TwilioVoicemailDetectionPlan VapiVoicemailDetectionPlanProvider: type: string enum: - vapi description: This is the provider to use for voicemail detection. title: VapiVoicemailDetectionPlanProvider VapiVoicemailDetectionPlanType: type: string enum: - audio - transcript description: |- This is the detection type to use for voicemail detection. - 'audio': Uses native audio models (default) - 'transcript': Uses ASR/transcript-based detection @default 'audio' (audio detection) title: VapiVoicemailDetectionPlanType VapiVoicemailDetectionPlan: type: object properties: beepMaxAwaitSeconds: type: number format: double default: 30 description: >- This is the maximum duration from the start of the call that we will wait for a voicemail beep, before speaking our message - If we detect a voicemail beep before this, we will speak the message at that point. - Setting too low a value means that the bot will start speaking its voicemail message too early. If it does so before the actual beep, it will get cut off. You should definitely tune this to your use case. @default 30 @min 0 @max 60 provider: $ref: '#/components/schemas/VapiVoicemailDetectionPlanProvider' description: This is the provider to use for voicemail detection. backoffPlan: $ref: '#/components/schemas/VoicemailDetectionBackoffPlan' description: This is the backoff plan for the voicemail detection. type: $ref: '#/components/schemas/VapiVoicemailDetectionPlanType' description: |- This is the detection type to use for voicemail detection. - 'audio': Uses native audio models (default) - 'transcript': Uses ASR/transcript-based detection @default 'audio' (audio detection) required: - provider title: VapiVoicemailDetectionPlan AssistantOverridesVoicemailDetection: oneOf: - $ref: '#/components/schemas/AssistantOverridesVoicemailDetection0' - $ref: '#/components/schemas/GoogleVoicemailDetectionPlan' - $ref: '#/components/schemas/OpenAIVoicemailDetectionPlan' - $ref: '#/components/schemas/TwilioVoicemailDetectionPlan' - $ref: '#/components/schemas/VapiVoicemailDetectionPlan' description: >- These are the settings to configure or disable voicemail detection. Alternatively, voicemail detection can be configured using the model.tools=[VoicemailTool]. By default, voicemail detection is disabled. title: AssistantOverridesVoicemailDetection AssistantOverridesClientMessages: type: string enum: - conversation-update - assistant.speechStarted - function-call - function-call-result - hang - language-changed - metadata - model-output - speech-update - status-update - transcript - tool-calls - tool-calls-result - tool.completed - transfer-update - user-interrupted - voice-input - workflow.node.started - assistant.started description: >- These are the messages that will be sent to your Client SDKs. Default is conversation-update,function-call,hang,model-output,speech-update,status-update,transfer-update,transcript,tool-calls,user-interrupted,voice-input,workflow.node.started,assistant.started. You can check the shape of the messages in ClientMessage schema. title: AssistantOverridesClientMessages AssistantOverridesServerMessages: type: string enum: - assistant.started - assistant.speechStarted - conversation-update - end-of-call-report - function-call - hang - language-changed - language-change-detected - model-output - phone-call-control - speech-update - status-update - transcript - transcript[transcriptType="final"] - tool-calls - transfer-destination-request - handoff-destination-request - transfer-update - user-interrupted - voice-input - chat.created - chat.deleted - session.created - session.updated - session.deleted - call.deleted - call.delete.failed description: >- These are the messages that will be sent to your Server URL. Default is conversation-update,end-of-call-report,function-call,hang,speech-update,status-update,tool-calls,transfer-destination-request,handoff-destination-request,user-interrupted,assistant.started. You can check the shape of the messages in ServerMessage schema. title: AssistantOverridesServerMessages AssistantOverridesBackgroundSound0: type: string enum: - 'off' - office title: AssistantOverridesBackgroundSound0 AssistantOverridesBackgroundSound: oneOf: - $ref: '#/components/schemas/AssistantOverridesBackgroundSound0' - type: string format: uri description: >- This is the background sound in the call. Default for phone calls is 'office' and default for web calls is 'off'. You can also provide a custom sound by providing a URL to an audio file. title: AssistantOverridesBackgroundSound TransportConfigurationTwilioProvider: type: string enum: - twilio title: TransportConfigurationTwilioProvider TransportConfigurationTwilioRecordingChannels: type: string enum: - mono - dual description: >- The number of channels in the final recording. Can be: `mono` or `dual`. The default is `mono`. `mono` records both legs of the call in a single channel of the recording file. `dual` records each leg to a separate channel of the recording file. The first channel of a dual-channel recording contains the parent call and the second channel contains the child call. @default 'mono' title: TransportConfigurationTwilioRecordingChannels TransportConfigurationTwilio: type: object properties: provider: $ref: '#/components/schemas/TransportConfigurationTwilioProvider' timeout: type: number format: double description: >- The integer number of seconds that we should allow the phone to ring before assuming there is no answer. The default is `60` seconds and the maximum is `600` seconds. For some call flows, we will add a 5-second buffer to the timeout value you provide. For this reason, a timeout value of 10 seconds could result in an actual timeout closer to 15 seconds. You can set this to a short time, such as `15` seconds, to hang up before reaching an answering machine or voicemail. @default 60 record: type: boolean description: |- Whether to record the call. Can be `true` to record the phone call, or `false` to not. The default is `false`. @default false recordingChannels: $ref: '#/components/schemas/TransportConfigurationTwilioRecordingChannels' description: >- The number of channels in the final recording. Can be: `mono` or `dual`. The default is `mono`. `mono` records both legs of the call in a single channel of the recording file. `dual` records each leg to a separate channel of the recording file. The first channel of a dual-channel recording contains the parent call and the second channel contains the child call. @default 'mono' required: - provider title: TransportConfigurationTwilio AssistantOverridesTransportConfigurationsItems: oneOf: - $ref: '#/components/schemas/TransportConfigurationTwilio' title: AssistantOverridesTransportConfigurationsItems LangfuseObservabilityPlanProvider: type: string enum: - langfuse title: LangfuseObservabilityPlanProvider LangfuseObservabilityPlanMetadata: type: object properties: {} description: >- This is a JSON object that will be added to the Langfuse trace. Traces can be enriched with metadata to better understand your users, application, and experiments. https://langfuse.com/docs/tracing-features/metadata By default it includes the call metadata, assistant metadata, and assistant overrides. title: LangfuseObservabilityPlanMetadata LangfuseObservabilityPlan: type: object properties: provider: $ref: '#/components/schemas/LangfuseObservabilityPlanProvider' promptName: type: string description: >- The name of a Langfuse prompt to link generations to. This enables tracking which prompt version was used for each generation. https://langfuse.com/docs/prompt-management/features/link-to-traces promptVersion: type: number format: double description: >- The version number of the Langfuse prompt to link generations to. Used together with promptName to identify the exact prompt version. https://langfuse.com/docs/prompt-management/features/link-to-traces traceName: type: string description: >- Custom name for the Langfuse trace. Supports Liquid templates. Available variables: - {{ call.id }} - Call UUID - {{ call.type }} - 'inboundPhoneCall', 'outboundPhoneCall', 'webCall' - {{ assistant.name }} - Assistant name - {{ assistant.id }} - Assistant ID Example: "{{ assistant.name }} - {{ call.type }}" Defaults to call ID if not provided. tags: type: array items: type: string description: >- This is an array of tags to be added to the Langfuse trace. Tags allow you to categorize and filter traces. https://langfuse.com/docs/tracing-features/tags metadata: $ref: '#/components/schemas/LangfuseObservabilityPlanMetadata' description: >- This is a JSON object that will be added to the Langfuse trace. Traces can be enriched with metadata to better understand your users, application, and experiments. https://langfuse.com/docs/tracing-features/metadata By default it includes the call metadata, assistant metadata, and assistant overrides. required: - provider - tags title: LangfuseObservabilityPlan UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockRegion: type: string enum: - us-east-1 - us-west-2 - eu-west-1 - eu-west-3 - ap-northeast-1 - ap-southeast-2 description: AWS region where Bedrock is configured. title: >- UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockRegion AwsiamCredentialsAuthenticationPlanType: type: string enum: - aws-iam title: AwsiamCredentialsAuthenticationPlanType AWSIAMCredentialsAuthenticationPlan: type: object properties: type: $ref: '#/components/schemas/AwsiamCredentialsAuthenticationPlanType' awsAccessKeyId: type: string description: AWS Access Key ID. This is not returned in the API. awsSecretAccessKey: type: string description: AWS Secret Access Key. This is not returned in the API. required: - type - awsAccessKeyId - awsSecretAccessKey title: AWSIAMCredentialsAuthenticationPlan AwsStsAuthenticationPlanType: type: string enum: - aws-sts description: This is the type of authentication plan title: AwsStsAuthenticationPlanType AWSStsAuthenticationPlan: type: object properties: type: $ref: '#/components/schemas/AwsStsAuthenticationPlanType' description: This is the type of authentication plan roleArn: type: string description: This is the role ARN for the AWS credential externalId: type: string description: >- Optional external ID for additional security in the role trust policy. required: - type - roleArn title: AWSStsAuthenticationPlan UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockAuthenticationPlan: oneOf: - $ref: '#/components/schemas/AWSIAMCredentialsAuthenticationPlan' - $ref: '#/components/schemas/AWSStsAuthenticationPlan' description: >- Authentication method - either direct IAM credentials or cross-account role assumption. title: >- UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockAuthenticationPlan UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiRegion: type: string enum: - australiaeast - canadaeast - canadacentral - centralus - eastus2 - eastus - france - germanywestcentral - india - japaneast - japanwest - northcentralus - norway - polandcentral - southcentralus - spaincentral - swedencentral - switzerland - uaenorth - uk - westeurope - westus - westus3 title: UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiRegion UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiModels: type: string enum: - gpt-5.4 - gpt-5.4-mini - gpt-5.4-nano - gpt-5.2 - gpt-5.2-chat - gpt-5.1 - gpt-5.1-chat - gpt-5 - gpt-5-mini - gpt-5-nano - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - gpt-4o-2024-11-20 - gpt-4o-2024-08-06 - gpt-4o-2024-05-13 - gpt-4o-mini-2024-07-18 - gpt-4-turbo-2024-04-09 - gpt-4-0125-preview - gpt-4-1106-preview - gpt-4-0613 - gpt-35-turbo-0125 - gpt-35-turbo-1106 title: UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiModels UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureService: type: string enum: - speech - blob_storage default: speech description: This is the service being used in Azure. title: UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureService UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureRegion: type: string enum: - australiaeast - canadaeast - canadacentral - centralus - eastus2 - eastus - france - germanywestcentral - india - japaneast - japanwest - northcentralus - norway - polandcentral - southcentralus - spaincentral - swedencentral - switzerland - uaenorth - uk - westeurope - westus - westus3 description: This is the region of the Azure resource. title: UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureRegion AzureBlobStorageBucketPlan: type: object properties: connectionString: type: string description: This is the blob storage connection string for the Azure resource. containerName: type: string description: This is the container name for the Azure blob storage. path: type: string description: >- This is the path where call artifacts will be stored. Usage: - To store call artifacts in a specific folder, set this to the full path. Eg. "/folder-name1/folder-name2". - To store call artifacts in the root of the bucket, leave this blank. @default "/" required: - connectionString - containerName title: AzureBlobStorageBucketPlan SipTrunkGatewayOutboundProtocol: type: string enum: - tls/srtp - tcp - tls - udp description: >- This is the protocol to use for SIP signaling outbound calls. Default is udp. @default udp title: SipTrunkGatewayOutboundProtocol SipTrunkGateway: type: object properties: ip: type: string description: >- This is the address of the gateway. It can be an IPv4 address like 1.1.1.1 or a fully qualified domain name like my-sip-trunk.pstn.twilio.com. port: type: number format: double description: |- This is the port number of the gateway. Default is 5060. @default 5060 netmask: type: number format: double description: |- This is the netmask of the gateway. Defaults to 32. @default 32 inboundEnabled: type: boolean description: >- This is whether inbound calls are allowed from this gateway. Default is true. @default true outboundEnabled: type: boolean description: >- This is whether outbound calls should be sent to this gateway. Default is true. Note, if netmask is less than 32, it doesn't affect the outbound IPs that are tried. 1 attempt is made to `ip:port`. @default true outboundProtocol: $ref: '#/components/schemas/SipTrunkGatewayOutboundProtocol' description: >- This is the protocol to use for SIP signaling outbound calls. Default is udp. @default udp optionsPingEnabled: type: boolean description: >- This is whether to send options ping to the gateway. This can be used to check if the gateway is reachable. Default is false. This is useful for high availability setups where you want to check if the gateway is reachable before routing calls to it. Note, if no gateway for a trunk is reachable, outbound calls will be rejected. @default false required: - ip title: SipTrunkGateway SipTrunkOutboundSipRegisterPlan: type: object properties: domain: type: string username: type: string realm: type: string title: SipTrunkOutboundSipRegisterPlan SipTrunkOutboundAuthenticationPlan: type: object properties: authPassword: type: string description: This is not returned in the API. authUsername: type: string sipRegisterPlan: $ref: '#/components/schemas/SipTrunkOutboundSipRegisterPlan' description: >- This can be used to configure if SIP register is required by the SIP trunk. If not provided, no SIP registration will be attempted. title: SipTrunkOutboundAuthenticationPlan SbcConfiguration: type: object properties: {} title: SbcConfiguration CreateCerebrasCredentialDtoProvider: type: string enum: - cerebras title: CreateCerebrasCredentialDtoProvider CloudflareR2BucketPlan: type: object properties: accessKeyId: type: string description: Cloudflare R2 Access key ID. secretAccessKey: type: string description: Cloudflare R2 access key secret. This is not returned in the API. url: type: string description: Cloudflare R2 base url. name: type: string description: This is the name of the bucket. path: type: string description: >- This is the path where call artifacts will be stored. Usage: - To store call artifacts in a specific folder, set this to the full path. Eg. "/folder-name1/folder-name2". - To store call artifacts in the root of the bucket, leave this blank. @default "/" required: - name title: CloudflareR2BucketPlan OAuth2AuthenticationPlan: type: object properties: url: type: string description: This is the OAuth2 URL. clientId: type: string description: This is the OAuth2 client ID. clientSecret: type: string description: This is the OAuth2 client secret. scope: type: string description: This is the scope of the OAuth2 token. required: - url - clientId - clientSecret title: OAuth2AuthenticationPlan GcpKey: type: object properties: type: type: string description: This is the type of the key. Most likely, this is "service_account". projectId: type: string description: This is the ID of the Google Cloud project associated with this key. privateKeyId: type: string description: This is the unique identifier for the private key. privateKey: type: string description: |- This is the private key in PEM format. Note: This is not returned in the API. clientEmail: type: string description: This is the email address associated with the service account. clientId: type: string description: This is the unique identifier for the client. authUri: type: string description: This is the URI for the auth provider's authorization endpoint. tokenUri: type: string description: This is the URI for the auth provider's token endpoint. authProviderX509CertUrl: type: string description: >- This is the URL of the public x509 certificate for the auth provider. clientX509CertUrl: type: string description: This is the URL of the public x509 certificate for the client. universeDomain: type: string description: >- This is the domain associated with the universe this service account belongs to. required: - type - projectId - privateKeyId - privateKey - clientEmail - clientId - authUri - tokenUri - authProviderX509CertUrl - clientX509CertUrl - universeDomain title: GcpKey BucketPlan: type: object properties: name: type: string description: This is the name of the bucket. region: type: string description: >- This is the region of the bucket. Usage: - If `credential.type` is `aws`, then this is required. - If `credential.type` is `gcp`, then this is optional since GCP allows buckets to be accessed without a region but region is required for data residency requirements. Read here: https://cloud.google.com/storage/docs/request-endpoints This overrides the `credential.region` field if it is provided. path: type: string description: >- This is the path where call artifacts will be stored. Usage: - To store call artifacts in a specific folder, set this to the full path. Eg. "/folder-name1/folder-name2". - To store call artifacts in the root of the bucket, leave this blank. @default "/" hmacAccessKey: type: string description: >- This is the HMAC access key offered by GCP for interoperability with S3 clients. Here is the guide on how to create: https://cloud.google.com/storage/docs/authentication/managing-hmackeys#console Usage: - If `credential.type` is `gcp`, then this is required. - If `credential.type` is `aws`, then this is not required since credential.awsAccessKeyId is used instead. hmacSecret: type: string description: >- This is the secret for the HMAC access key. Here is the guide on how to create: https://cloud.google.com/storage/docs/authentication/managing-hmackeys#console Usage: - If `credential.type` is `gcp`, then this is required. - If `credential.type` is `aws`, then this is not required since credential.awsSecretAccessKey is used instead. Note: This is not returned in the API. required: - name title: BucketPlan CreateGoogleCredentialDtoProvider: type: string enum: - google description: >- This is the key for Gemini in Google AI Studio. Get it from here: https://aistudio.google.com/app/apikey title: CreateGoogleCredentialDtoProvider CreateInflectionAiCredentialDtoProvider: type: string enum: - inflection-ai description: >- This is the api key for Pi in InflectionAI's console. Get it from here: https://developers.inflection.ai/keys, billing will need to be setup title: CreateInflectionAiCredentialDtoProvider SupabaseBucketPlanRegion: type: string enum: - us-west-1 - us-east-1 - us-east-2 - ca-central-1 - eu-west-1 - eu-west-2 - eu-west-3 - eu-central-1 - eu-central-2 - eu-north-1 - ap-south-1 - ap-southeast-1 - ap-northeast-1 - ap-northeast-2 - ap-southeast-2 - sa-east-1 description: >- This is the S3 Region. It should look like us-east-1 It should be one of the supabase regions defined in the SUPABASE_REGION enum Check https://supabase.com/docs/guides/platform/regions for up to date regions title: SupabaseBucketPlanRegion SupabaseBucketPlan: type: object properties: region: $ref: '#/components/schemas/SupabaseBucketPlanRegion' description: >- This is the S3 Region. It should look like us-east-1 It should be one of the supabase regions defined in the SUPABASE_REGION enum Check https://supabase.com/docs/guides/platform/regions for up to date regions url: type: string description: |- This is the S3 compatible URL for Supabase S3 This should look like https://.supabase.co/storage/v1/s3 accessKeyId: type: string description: |- This is the Supabase S3 Access Key ID. The user creates this in the Supabase project Storage settings secretAccessKey: type: string description: >- This is the Supabase S3 Secret Access Key. The user creates this in the Supabase project Storage settings along with the access key id name: type: string description: >- This is the Supabase S3 Bucket Name. The user must create this in Supabase under Storage > Buckets A bucket that does not exist will not be checked now, but file uploads will fail path: type: string description: >- This is the Supabase S3 Bucket Folder Path. The user can create this in Supabase under Storage > Buckets A path that does not exist will not be checked now, but file uploads will fail A Path is like a folder in the bucket Eg. If the bucket is called "my-bucket" and the path is "my-folder", the full path is "my-bucket/my-folder" required: - region - url - accessKeyId - secretAccessKey - name title: SupabaseBucketPlan HmacAuthenticationPlanType: type: string enum: - hmac title: HmacAuthenticationPlanType HmacAuthenticationPlanAlgorithm: type: string enum: - sha256 - sha512 - sha1 description: This is the HMAC algorithm to use for signing. title: HmacAuthenticationPlanAlgorithm HmacAuthenticationPlanSignatureEncoding: type: string enum: - hex - base64 description: The encoding format for the signature. Defaults to 'hex'. title: HmacAuthenticationPlanSignatureEncoding BearerAuthenticationPlanType: type: string enum: - bearer title: BearerAuthenticationPlanType UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingWebhookAuthenticationPlan: oneOf: - type: object properties: type: type: string enum: - oauth2 description: 'Discriminator value: oauth2' url: type: string description: This is the OAuth2 URL. clientId: type: string description: This is the OAuth2 client ID. clientSecret: type: string description: This is the OAuth2 client secret. scope: type: string description: This is the scope of the OAuth2 token. required: - type - url - clientId - clientSecret description: oauth2 variant - type: object properties: type: $ref: '#/components/schemas/HmacAuthenticationPlanType' secretKey: type: string description: This is the HMAC secret key used to sign requests. algorithm: $ref: '#/components/schemas/HmacAuthenticationPlanAlgorithm' description: This is the HMAC algorithm to use for signing. signatureHeader: type: string description: >- This is the header name where the signature will be sent. Defaults to 'x-signature'. timestampHeader: type: string description: >- This is the header name where the timestamp will be sent. Defaults to 'x-timestamp'. signaturePrefix: type: string description: >- This is the prefix for the signature. For example, 'sha256=' for GitHub-style signatures. includeTimestamp: type: boolean description: >- Whether to include a timestamp in the signature payload. Defaults to true. payloadFormat: type: string description: >- Custom payload format. Use {body} for request body, {timestamp} for timestamp, {method} for HTTP method, {url} for URL, {svix-id} for unique message ID. Defaults to '{timestamp}.{body}'. messageIdHeader: type: string description: >- This is the header name where the unique message ID will be sent. Used for Svix-style webhooks. signatureEncoding: $ref: '#/components/schemas/HmacAuthenticationPlanSignatureEncoding' description: The encoding format for the signature. Defaults to 'hex'. secretIsBase64: type: boolean description: >- Whether the secret key is base64-encoded and should be decoded before use. Defaults to false. required: - type - secretKey - algorithm description: hmac variant - type: object properties: type: $ref: '#/components/schemas/BearerAuthenticationPlanType' token: type: string description: This is the bearer token value. headerName: type: string description: >- This is the header name where the bearer token will be sent. Defaults to 'Authorization'. bearerPrefixEnabled: type: boolean description: >- Whether to include the 'Bearer ' prefix in the header value. Defaults to true. required: - type - token description: bearer variant discriminator: propertyName: type description: >- This is the authentication plan. Supports OAuth2 RFC 6749, HMAC signing, and Bearer authentication. title: >- UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingWebhookAuthenticationPlan CreateCustomCredentialDtoProvider: type: string enum: - custom-credential title: CreateCustomCredentialDtoProvider CreateCustomCredentialDtoAuthenticationPlan: oneOf: - type: object properties: type: type: string enum: - oauth2 description: 'Discriminator value: oauth2' url: type: string description: This is the OAuth2 URL. clientId: type: string description: This is the OAuth2 client ID. clientSecret: type: string description: This is the OAuth2 client secret. scope: type: string description: This is the scope of the OAuth2 token. required: - type - url - clientId - clientSecret description: oauth2 variant - type: object properties: type: $ref: '#/components/schemas/HmacAuthenticationPlanType' secretKey: type: string description: This is the HMAC secret key used to sign requests. algorithm: $ref: '#/components/schemas/HmacAuthenticationPlanAlgorithm' description: This is the HMAC algorithm to use for signing. signatureHeader: type: string description: >- This is the header name where the signature will be sent. Defaults to 'x-signature'. timestampHeader: type: string description: >- This is the header name where the timestamp will be sent. Defaults to 'x-timestamp'. signaturePrefix: type: string description: >- This is the prefix for the signature. For example, 'sha256=' for GitHub-style signatures. includeTimestamp: type: boolean description: >- Whether to include a timestamp in the signature payload. Defaults to true. payloadFormat: type: string description: >- Custom payload format. Use {body} for request body, {timestamp} for timestamp, {method} for HTTP method, {url} for URL, {svix-id} for unique message ID. Defaults to '{timestamp}.{body}'. messageIdHeader: type: string description: >- This is the header name where the unique message ID will be sent. Used for Svix-style webhooks. signatureEncoding: $ref: '#/components/schemas/HmacAuthenticationPlanSignatureEncoding' description: The encoding format for the signature. Defaults to 'hex'. secretIsBase64: type: boolean description: >- Whether the secret key is base64-encoded and should be decoded before use. Defaults to false. required: - type - secretKey - algorithm description: hmac variant - type: object properties: type: $ref: '#/components/schemas/BearerAuthenticationPlanType' token: type: string description: This is the bearer token value. headerName: type: string description: >- This is the header name where the bearer token will be sent. Defaults to 'Authorization'. bearerPrefixEnabled: type: boolean description: >- Whether to include the 'Bearer ' prefix in the header value. Defaults to true. required: - type - token description: bearer variant discriminator: propertyName: type description: >- This is the authentication plan. Supports OAuth2 RFC 6749, HMAC signing, and Bearer authentication. title: CreateCustomCredentialDtoAuthenticationPlan PublicKeyEncryptionPlanType: type: string enum: - public-key description: The type of encryption plan. title: PublicKeyEncryptionPlanType PublicKeyEncryptionPlanAlgorithm: type: string enum: - RSA-OAEP-256 description: The encryption algorithm to use. title: PublicKeyEncryptionPlanAlgorithm SpkiPemPublicKeyConfigFormat: type: string enum: - spki-pem description: The format of the public key. title: SpkiPemPublicKeyConfigFormat SpkiPemPublicKeyConfig: type: object properties: name: type: string description: Optional name of the key for identification purposes. format: $ref: '#/components/schemas/SpkiPemPublicKeyConfigFormat' description: The format of the public key. pem: type: string description: The PEM-encoded public key. required: - format - pem title: SpkiPemPublicKeyConfig PublicKeyEncryptionPlan: type: object properties: type: $ref: '#/components/schemas/PublicKeyEncryptionPlanType' description: The type of encryption plan. algorithm: $ref: '#/components/schemas/PublicKeyEncryptionPlanAlgorithm' description: The encryption algorithm to use. publicKey: $ref: '#/components/schemas/SpkiPemPublicKeyConfig' description: The public key configuration. required: - type - algorithm - publicKey title: PublicKeyEncryptionPlan CreateNeuphonicCredentialDtoProvider: type: string enum: - neuphonic title: CreateNeuphonicCredentialDtoProvider CreateHumeCredentialDtoProvider: type: string enum: - hume title: CreateHumeCredentialDtoProvider CreateMistralCredentialDtoProvider: type: string enum: - mistral title: CreateMistralCredentialDtoProvider CreateSpeechmaticsCredentialDtoProvider: type: string enum: - speechmatics title: CreateSpeechmaticsCredentialDtoProvider CreateSonioxCredentialDtoProvider: type: string enum: - soniox title: CreateSonioxCredentialDtoProvider CreateTrieveCredentialDtoProvider: type: string enum: - trieve title: CreateTrieveCredentialDtoProvider CreateGoHighLevelMcpCredentialDtoProvider: type: string enum: - ghl.oauth2-authorization title: CreateGoHighLevelMcpCredentialDtoProvider Oauth2AuthenticationSession: type: object properties: accessToken: type: string description: This is the OAuth2 access token. expiresAt: type: string format: date-time description: This is the OAuth2 access token expiration. refreshToken: type: string description: This is the OAuth2 refresh token. title: Oauth2AuthenticationSession CreateInworldCredentialDtoProvider: type: string enum: - inworld title: CreateInworldCredentialDtoProvider CreateWellSaidCredentialDtoProvider: type: string enum: - wellsaid title: CreateWellSaidCredentialDtoProvider CreateEmailCredentialDtoProvider: type: string enum: - email title: CreateEmailCredentialDtoProvider CreateSlackWebhookCredentialDtoProvider: type: string enum: - slack-webhook title: CreateSlackWebhookCredentialDtoProvider AssistantOverridesCredentialsItems: oneOf: - type: object properties: provider: type: string enum: - 11labs description: 'Discriminator value: 11labs' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateElevenLabsCredentialDTO variant - type: object properties: provider: type: string enum: - anthropic description: 'Discriminator value: anthropic' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateAnthropicCredentialDTO variant - type: object properties: provider: type: string enum: - anthropic-bedrock description: 'Discriminator value: anthropic-bedrock' region: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockRegion description: AWS region where Bedrock is configured. authenticationPlan: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockAuthenticationPlan description: >- Authentication method - either direct IAM credentials or cross-account role assumption. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - region - authenticationPlan description: anthropic-bedrock variant - type: object properties: provider: type: string enum: - anyscale description: 'Discriminator value: anyscale' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateAnyscaleCredentialDTO variant - type: object properties: provider: type: string enum: - assembly-ai description: 'Discriminator value: assembly-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateAssemblyAICredentialDTO variant - type: object properties: provider: type: string enum: - azure-openai description: 'Discriminator value: azure-openai' region: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiRegion models: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiModels openAIKey: type: string description: This is not returned in the API. ocpApimSubscriptionKey: type: string description: This is not returned in the API. openAIEndpoint: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - region - models - openAIKey - openAIEndpoint description: CreateAzureOpenAICredentialDTO variant - type: object properties: provider: type: string enum: - azure description: 'Discriminator value: azure' service: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureService description: This is the service being used in Azure. region: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureRegion description: This is the region of the Azure resource. apiKey: type: string description: This is not returned in the API. fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/AzureBlobStorageBucketPlan' description: >- This is the bucket plan that can be provided to store call artifacts in Azure Blob Storage. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - service description: CreateAzureCredentialDTO variant - type: object properties: provider: type: string enum: - byo-sip-trunk description: 'Discriminator value: byo-sip-trunk' gateways: type: array items: $ref: '#/components/schemas/SipTrunkGateway' description: This is the list of SIP trunk's gateways. outboundAuthenticationPlan: $ref: '#/components/schemas/SipTrunkOutboundAuthenticationPlan' description: >- This can be used to configure the outbound authentication if required by the SIP trunk. outboundLeadingPlusEnabled: type: boolean description: >- This ensures the outbound origination attempts have a leading plus. Defaults to false to match conventional telecom behavior. Usage: - Vonage/Twilio requires leading plus for all outbound calls. Set this to true. @default false techPrefix: type: string description: >- This can be used to configure the tech prefix on outbound calls. This is an advanced property. sipDiversionHeader: type: string description: >- This can be used to enable the SIP diversion header for authenticating the calling number if the SIP trunk supports it. This is an advanced property. sbcConfiguration: $ref: '#/components/schemas/SbcConfiguration' description: >- This is an advanced configuration for enterprise deployments. This uses the onprem SBC to trunk into the SIP trunk's `gateways`, rather than the managed SBC provided by Vapi. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - gateways description: CreateByoSipTrunkCredentialDTO variant - type: object properties: provider: type: string enum: - cartesia description: 'Discriminator value: cartesia' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateCartesiaCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateCerebrasCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateCerebrasCredentialDTO variant - type: object properties: provider: type: string enum: - cloudflare description: 'Discriminator value: cloudflare' accountId: type: string description: Cloudflare Account Id. apiKey: type: string description: Cloudflare API Key / Token. accountEmail: type: string description: Cloudflare Account Email. fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/CloudflareR2BucketPlan' description: >- This is the bucket plan that can be provided to store call artifacts in R2 name: type: string description: This is the name of credential. This is just for your reference. required: - provider description: CreateCloudflareCredentialDTO variant - type: object properties: provider: type: string enum: - custom-llm description: 'Discriminator value: custom-llm' apiKey: type: string description: This is not returned in the API. authenticationPlan: $ref: '#/components/schemas/OAuth2AuthenticationPlan' description: >- This is the authentication plan. Currently supports OAuth2 RFC 6749. To use Bearer authentication, use apiKey name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateCustomLLMCredentialDTO variant - type: object properties: provider: type: string enum: - deepgram description: 'Discriminator value: deepgram' apiKey: type: string description: This is not returned in the API. apiUrl: type: string description: >- This can be used to point to an onprem Deepgram instance. Defaults to api.deepgram.com. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateDeepgramCredentialDTO variant - type: object properties: provider: type: string enum: - deepinfra description: 'Discriminator value: deepinfra' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateDeepInfraCredentialDTO variant - type: object properties: provider: type: string enum: - deep-seek description: 'Discriminator value: deep-seek' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateDeepSeekCredentialDTO variant - type: object properties: provider: type: string enum: - gcp description: 'Discriminator value: gcp' fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. gcpKey: $ref: '#/components/schemas/GcpKey' description: >- This is the GCP key. This is the JSON that can be generated in the Google Cloud Console at https://console.cloud.google.com/iam-admin/serviceaccounts/details//keys. The schema is identical to the JSON that GCP outputs. region: type: string description: This is the region of the GCP resource. bucketPlan: $ref: '#/components/schemas/BucketPlan' name: type: string description: This is the name of credential. This is just for your reference. required: - provider - gcpKey description: CreateGcpCredentialDTO variant - type: object properties: provider: type: string enum: - gladia description: 'Discriminator value: gladia' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGladiaCredentialDTO variant - type: object properties: provider: type: string enum: - gohighlevel description: 'Discriminator value: gohighlevel' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGoHighLevelCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateGoogleCredentialDtoProvider' description: >- This is the key for Gemini in Google AI Studio. Get it from here: https://aistudio.google.com/app/apikey apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGoogleCredentialDTO variant - type: object properties: provider: type: string enum: - groq description: 'Discriminator value: groq' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGroqCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateInflectionAiCredentialDtoProvider' description: >- This is the api key for Pi in InflectionAI's console. Get it from here: https://developers.inflection.ai/keys, billing will need to be setup apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateInflectionAICredentialDTO variant - type: object properties: provider: type: string enum: - langfuse description: 'Discriminator value: langfuse' publicKey: type: string description: 'The public key for Langfuse project. Eg: pk-lf-...' apiKey: type: string description: >- The secret key for Langfuse project. Eg: sk-lf-... .This is not returned in the API. apiUrl: type: string description: >- The host URL for Langfuse project. Eg: https://cloud.langfuse.com name: type: string description: This is the name of credential. This is just for your reference. required: - provider - publicKey - apiKey - apiUrl description: CreateLangfuseCredentialDTO variant - type: object properties: provider: type: string enum: - lmnt description: 'Discriminator value: lmnt' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateLmntCredentialDTO variant - type: object properties: provider: type: string enum: - make description: 'Discriminator value: make' teamId: type: string description: Team ID region: type: string description: 'Region of your application. For example: eu1, eu2, us1, us2' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - teamId - region - apiKey description: CreateMakeCredentialDTO variant - type: object properties: provider: type: string enum: - openai description: 'Discriminator value: openai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateOpenAICredentialDTO variant - type: object properties: provider: type: string enum: - openrouter description: 'Discriminator value: openrouter' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateOpenRouterCredentialDTO variant - type: object properties: provider: type: string enum: - perplexity-ai description: 'Discriminator value: perplexity-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreatePerplexityAICredentialDTO variant - type: object properties: provider: type: string enum: - playht description: 'Discriminator value: playht' apiKey: type: string description: This is not returned in the API. userId: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey - userId description: CreatePlayHTCredentialDTO variant - type: object properties: provider: type: string enum: - rime-ai description: 'Discriminator value: rime-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateRimeAICredentialDTO variant - type: object properties: provider: type: string enum: - runpod description: 'Discriminator value: runpod' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateRunpodCredentialDTO variant - type: object properties: provider: type: string enum: - s3 description: 'Discriminator value: s3' awsAccessKeyId: type: string description: AWS access key ID. awsSecretAccessKey: type: string description: AWS access key secret. This is not returned in the API. region: type: string description: AWS region in which the S3 bucket is located. s3BucketName: type: string description: AWS S3 bucket name. s3PathPrefix: type: string description: The path prefix for the uploaded recording. Ex. "recordings/" fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - awsAccessKeyId - awsSecretAccessKey - region - s3BucketName - s3PathPrefix description: CreateS3CredentialDTO variant - type: object properties: provider: type: string enum: - supabase description: 'Discriminator value: supabase' fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/SupabaseBucketPlan' name: type: string description: This is the name of credential. This is just for your reference. required: - provider description: CreateSupabaseCredentialDTO variant - type: object properties: provider: type: string enum: - smallest-ai description: 'Discriminator value: smallest-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateSmallestAICredentialDTO variant - type: object properties: provider: type: string enum: - tavus description: 'Discriminator value: tavus' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateTavusCredentialDTO variant - type: object properties: provider: type: string enum: - together-ai description: 'Discriminator value: together-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateTogetherAICredentialDTO variant - type: object properties: provider: type: string enum: - twilio description: 'Discriminator value: twilio' authToken: type: string description: This is not returned in the API. apiKey: type: string description: This is not returned in the API. apiSecret: type: string description: This is not returned in the API. accountSid: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - accountSid description: CreateTwilioCredentialDTO variant - type: object properties: provider: type: string enum: - vonage description: 'Discriminator value: vonage' apiSecret: type: string description: This is not returned in the API. apiKey: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiSecret - apiKey description: CreateVonageCredentialDTO variant - type: object properties: provider: type: string enum: - webhook description: 'Discriminator value: webhook' authenticationPlan: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingWebhookAuthenticationPlan description: >- This is the authentication plan. Supports OAuth2 RFC 6749, HMAC signing, and Bearer authentication. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authenticationPlan description: CreateWebhookCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateCustomCredentialDtoProvider' authenticationPlan: $ref: '#/components/schemas/CreateCustomCredentialDtoAuthenticationPlan' description: >- This is the authentication plan. Supports OAuth2 RFC 6749, HMAC signing, and Bearer authentication. encryptionPlan: $ref: '#/components/schemas/PublicKeyEncryptionPlan' description: >- This is the encryption plan for encrypting sensitive data. Currently supports public-key encryption. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authenticationPlan description: custom-credential variant - type: object properties: provider: type: string enum: - xai description: 'Discriminator value: xai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateXAiCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateNeuphonicCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateNeuphonicCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateHumeCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateHumeCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateMistralCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateMistralCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateSpeechmaticsCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateSpeechmaticsCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateSonioxCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: soniox variant - type: object properties: provider: $ref: '#/components/schemas/CreateTrieveCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateTrieveCredentialDTO variant - type: object properties: provider: type: string enum: - google.calendar.oauth2-client description: 'Discriminator value: google.calendar.oauth2-client' name: type: string description: This is the name of credential. This is just for your reference. required: - provider description: CreateGoogleCalendarOAuth2ClientCredentialDTO variant - type: object properties: provider: type: string enum: - google.calendar.oauth2-authorization description: 'Discriminator value: google.calendar.oauth2-authorization' authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authorizationId description: CreateGoogleCalendarOAuth2AuthorizationCredentialDTO variant - type: object properties: provider: type: string enum: - google.sheets.oauth2-authorization description: 'Discriminator value: google.sheets.oauth2-authorization' authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authorizationId description: CreateGoogleSheetsOAuth2AuthorizationCredentialDTO variant - type: object properties: provider: type: string enum: - slack.oauth2-authorization description: 'Discriminator value: slack.oauth2-authorization' authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authorizationId description: CreateSlackOAuth2AuthorizationCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateGoHighLevelMcpCredentialDtoProvider' authenticationSession: $ref: '#/components/schemas/Oauth2AuthenticationSession' description: This is the authentication session for the credential. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authenticationSession description: CreateGoHighLevelMCPCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateInworldCredentialDtoProvider' apiKey: type: string description: >- This is the Inworld Basic (Base64) authentication token. This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: inworld variant - type: object properties: provider: type: string enum: - minimax description: 'Discriminator value: minimax' apiKey: type: string description: This is not returned in the API. groupId: type: string description: This is the Minimax Group ID. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey - groupId description: minimax variant - type: object properties: provider: $ref: '#/components/schemas/CreateWellSaidCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: wellsaid variant - type: object properties: provider: $ref: '#/components/schemas/CreateEmailCredentialDtoProvider' email: type: string description: The recipient email address for alerts name: type: string description: This is the name of credential. This is just for your reference. required: - provider - email description: email variant - type: object properties: provider: $ref: '#/components/schemas/CreateSlackWebhookCredentialDtoProvider' webhookUrl: type: string description: >- Slack incoming webhook URL. See https://api.slack.com/messaging/webhooks for setup instructions. This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - webhookUrl description: slack-webhook variant discriminator: propertyName: provider title: AssistantOverridesCredentialsItems CallHookCallEndingOn: type: string enum: - call.ending description: This is the event that triggers this hook title: CallHookCallEndingOn ToolCallHookActionType: type: string enum: - tool description: This is the type of action - must be "tool" title: ToolCallHookActionType ToolCallHookActionTool: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' description: >- This is the tool to call. To use an existing tool, send `toolId` instead. title: ToolCallHookActionTool ToolCallHookAction: type: object properties: type: $ref: '#/components/schemas/ToolCallHookActionType' description: This is the type of action - must be "tool" tool: $ref: '#/components/schemas/ToolCallHookActionTool' description: >- This is the tool to call. To use an existing tool, send `toolId` instead. toolId: type: string description: >- This is the tool to call. To use a transient tool, send `tool` instead. required: - type title: ToolCallHookAction MessageAddHookActionType: type: string enum: - message.add description: This is the type of action - must be "message.add" title: MessageAddHookActionType MessageAddHookAction: type: object properties: type: $ref: '#/components/schemas/MessageAddHookActionType' description: This is the type of action - must be "message.add" message: $ref: '#/components/schemas/OpenAIMessage' description: The message to add to the conversation in OpenAI format triggerResponseEnabled: type: boolean default: true description: Whether to trigger an assistant response after adding the message required: - type - message title: MessageAddHookAction CallHookCallEndingDoItems: oneOf: - $ref: '#/components/schemas/ToolCallHookAction' - $ref: '#/components/schemas/MessageAddHookAction' title: CallHookCallEndingDoItems CallHookFilterType: type: string enum: - oneOf description: This is the type of filter - currently only "oneOf" is supported title: CallHookFilterType CallHookFilter: type: object properties: type: $ref: '#/components/schemas/CallHookFilterType' description: This is the type of filter - currently only "oneOf" is supported key: type: string description: This is the key to filter on (e.g. "call.endedReason") oneOf: type: array items: type: string description: This is the array of possible values to match against required: - type - key - oneOf title: CallHookFilter CallHookCallEnding: type: object properties: 'on': $ref: '#/components/schemas/CallHookCallEndingOn' description: This is the event that triggers this hook do: type: array items: $ref: '#/components/schemas/CallHookCallEndingDoItems' description: This is the set of actions to perform when the hook triggers filters: type: array items: $ref: '#/components/schemas/CallHookFilter' description: This is the set of filters that must match for the hook to trigger required: - 'on' - do title: CallHookCallEnding CallHookAssistantSpeechInterruptedOn: type: string enum: - assistant.speech.interrupted description: This is the event that triggers this hook title: CallHookAssistantSpeechInterruptedOn SayHookActionType: type: string enum: - say description: This is the type of action - must be "say" title: SayHookActionType AssistantMessageRole: type: string enum: - assistant default: assistant description: This is the role of the message author title: AssistantMessageRole ToolCallFunction: type: object properties: arguments: type: string description: This is the arguments to call the function with name: type: string description: This is the name of the function to call required: - arguments - name title: ToolCallFunction ToolCall: type: object properties: id: type: string description: This is the ID of the tool call type: type: string description: This is the type of tool function: $ref: '#/components/schemas/ToolCallFunction' description: This is the function that was called required: - id - type - function title: ToolCall AssistantMessageMetadata: type: object properties: {} description: This is an optional metadata for the message title: AssistantMessageMetadata AssistantMessage: type: object properties: role: $ref: '#/components/schemas/AssistantMessageRole' description: This is the role of the message author content: type: string description: This is the content of the assistant message refusal: type: string description: This is the refusal message generated by the model tool_calls: type: array items: $ref: '#/components/schemas/ToolCall' description: This is the tool calls generated by the model name: type: string description: This is an optional name for the participant metadata: $ref: '#/components/schemas/AssistantMessageMetadata' description: This is an optional metadata for the message required: - role title: AssistantMessage ToolMessageRole: type: string enum: - tool default: tool description: This is the role of the message author title: ToolMessageRole ToolMessageMetadata: type: object properties: {} description: This is an optional metadata for the message title: ToolMessageMetadata ToolMessage: type: object properties: role: $ref: '#/components/schemas/ToolMessageRole' description: This is the role of the message author content: type: string description: This is the content of the tool message tool_call_id: type: string description: This is the ID of the tool call this message is responding to name: type: string description: This is an optional name for the participant metadata: $ref: '#/components/schemas/ToolMessageMetadata' description: This is an optional metadata for the message required: - role - content - tool_call_id title: ToolMessage DeveloperMessageRole: type: string enum: - developer default: developer description: This is the role of the message author title: DeveloperMessageRole DeveloperMessageMetadata: type: object properties: {} description: This is an optional metadata for the message title: DeveloperMessageMetadata DeveloperMessage: type: object properties: role: $ref: '#/components/schemas/DeveloperMessageRole' description: This is the role of the message author content: type: string description: This is the content of the developer message name: type: string description: This is an optional name for the participant metadata: $ref: '#/components/schemas/DeveloperMessageMetadata' description: This is an optional metadata for the message required: - role - content title: DeveloperMessage SayHookActionPromptOneOf1Items: oneOf: - $ref: '#/components/schemas/SystemMessage' - $ref: '#/components/schemas/UserMessage' - $ref: '#/components/schemas/AssistantMessage' - $ref: '#/components/schemas/ToolMessage' - $ref: '#/components/schemas/DeveloperMessage' title: SayHookActionPromptOneOf1Items SayHookActionPrompt1: type: array items: $ref: '#/components/schemas/SayHookActionPromptOneOf1Items' title: SayHookActionPrompt1 SayHookActionPrompt: oneOf: - type: string - $ref: '#/components/schemas/SayHookActionPrompt1' description: >- This is the prompt for the assistant to generate a response based on existing conversation. Can be a string or an array of chat messages. title: SayHookActionPrompt SayHookActionExact: type: object properties: {} description: This is the message to say title: SayHookActionExact SayHookAction: type: object properties: type: $ref: '#/components/schemas/SayHookActionType' description: This is the type of action - must be "say" prompt: $ref: '#/components/schemas/SayHookActionPrompt' description: >- This is the prompt for the assistant to generate a response based on existing conversation. Can be a string or an array of chat messages. exact: $ref: '#/components/schemas/SayHookActionExact' description: This is the message to say required: - type title: SayHookAction CallHookAssistantSpeechInterruptedDoItems: oneOf: - $ref: '#/components/schemas/SayHookAction' - $ref: '#/components/schemas/ToolCallHookAction' - $ref: '#/components/schemas/MessageAddHookAction' title: CallHookAssistantSpeechInterruptedDoItems CallHookAssistantSpeechInterrupted: type: object properties: 'on': $ref: '#/components/schemas/CallHookAssistantSpeechInterruptedOn' description: This is the event that triggers this hook do: type: array items: $ref: '#/components/schemas/CallHookAssistantSpeechInterruptedDoItems' description: This is the set of actions to perform when the hook triggers required: - 'on' - do title: CallHookAssistantSpeechInterrupted CallHookCustomerSpeechInterruptedOn: type: string enum: - customer.speech.interrupted description: This is the event that triggers this hook title: CallHookCustomerSpeechInterruptedOn CallHookCustomerSpeechInterruptedDoItems: oneOf: - $ref: '#/components/schemas/SayHookAction' - $ref: '#/components/schemas/ToolCallHookAction' - $ref: '#/components/schemas/MessageAddHookAction' title: CallHookCustomerSpeechInterruptedDoItems CallHookCustomerSpeechInterrupted: type: object properties: 'on': $ref: '#/components/schemas/CallHookCustomerSpeechInterruptedOn' description: This is the event that triggers this hook do: type: array items: $ref: '#/components/schemas/CallHookCustomerSpeechInterruptedDoItems' description: This is the set of actions to perform when the hook triggers required: - 'on' - do title: CallHookCustomerSpeechInterrupted CallHookCustomerSpeechTimeoutDoItems: oneOf: - $ref: '#/components/schemas/SayHookAction' - $ref: '#/components/schemas/ToolCallHookAction' - $ref: '#/components/schemas/MessageAddHookAction' title: CallHookCustomerSpeechTimeoutDoItems CustomerSpeechTimeoutOptionsTriggerResetMode: type: object properties: {} description: |- This is whether the counter for hook trigger resets the user speaks. @default never title: CustomerSpeechTimeoutOptionsTriggerResetMode CustomerSpeechTimeoutOptions: type: object properties: timeoutSeconds: type: number format: double description: >- This is the timeout in seconds before action is triggered. The clock starts when the assistant finishes speaking and remains active until the user speaks. @default 7.5 triggerMaxCount: type: number format: double description: |- This is the maximum number of times the hook will trigger in a call. @default 3 triggerResetMode: $ref: '#/components/schemas/CustomerSpeechTimeoutOptionsTriggerResetMode' description: |- This is whether the counter for hook trigger resets the user speaks. @default never required: - timeoutSeconds title: CustomerSpeechTimeoutOptions CallHookCustomerSpeechTimeout: type: object properties: 'on': type: string description: >- Must be either "customer.speech.timeout" or match the pattern "customer.speech.timeout[property=value]" do: type: array items: $ref: '#/components/schemas/CallHookCustomerSpeechTimeoutDoItems' description: This is the set of actions to perform when the hook triggers options: $ref: '#/components/schemas/CustomerSpeechTimeoutOptions' description: This is the set of filters that must match for the hook to trigger name: type: string description: >- This is the name of the hook, it can be set by the user to identify the hook. If no name is provided, the hook will be auto generated as UUID. @default UUID required: - 'on' - do title: CallHookCustomerSpeechTimeout SessionCreatedHookOn: type: string enum: - session.created description: This is the event that triggers this hook title: SessionCreatedHookOn SessionCreatedHookDoItems: oneOf: - $ref: '#/components/schemas/ToolCallHookAction' title: SessionCreatedHookDoItems SessionCreatedHook: type: object properties: 'on': $ref: '#/components/schemas/SessionCreatedHookOn' description: This is the event that triggers this hook do: type: array items: $ref: '#/components/schemas/SessionCreatedHookDoItems' description: This is the set of actions to perform when the hook triggers. name: type: string description: |- Optional name for this hook instance. If no name is provided, the hook will be auto generated as UUID. @default UUID required: - 'on' - do title: SessionCreatedHook AssistantOverridesHooksItems: oneOf: - $ref: '#/components/schemas/CallHookCallEnding' - $ref: '#/components/schemas/CallHookAssistantSpeechInterrupted' - $ref: '#/components/schemas/CallHookCustomerSpeechInterrupted' - $ref: '#/components/schemas/CallHookCustomerSpeechTimeout' - $ref: '#/components/schemas/SessionCreatedHook' title: AssistantOverridesHooksItems AssistantOverridesToolsAppendItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: AssistantOverridesToolsAppendItems AssistantOverridesVariableValues: type: object properties: {} description: >- These are values that will be used to replace the template variables in the assistant messages and other text-based fields. This uses LiquidJS syntax. https://liquidjs.com/tutorials/intro-to-liquid.html So for example, `{{ name }}` will be replaced with the value of `name` in `variableValues`. `{{"now" | date: "%b %d, %Y, %I:%M %p", "America/New_York"}}` will be replaced with the current date and time in New York. Some VAPI reserved defaults: - *customer* - the customer object title: AssistantOverridesVariableValues SecurityFilterBase: type: object properties: {} title: SecurityFilterBase SecurityFilterPlanMode: type: string enum: - sanitize - reject - replace default: sanitize description: |- Mode of operation when a security threat is detected. - 'sanitize': Remove or replace the threatening content - 'reject': Replace the entire transcript with replacement text - 'replace': Replace threatening patterns with replacement text @default 'sanitize' title: SecurityFilterPlanMode SecurityFilterPlan: type: object properties: enabled: type: boolean default: false description: |- Whether the security filter is enabled. @default false filters: type: array items: $ref: '#/components/schemas/SecurityFilterBase' description: |- Array of security filter types to apply. If array is not empty, only those security filters are run. mode: $ref: '#/components/schemas/SecurityFilterPlanMode' description: |- Mode of operation when a security threat is detected. - 'sanitize': Remove or replace the threatening content - 'reject': Replace the entire transcript with replacement text - 'replace': Replace threatening patterns with replacement text @default 'sanitize' replacementText: type: string default: '[FILTERED]' description: |- Text to use when replacing filtered content. @default '[FILTERED]' title: SecurityFilterPlan CompliancePlanRecordingConsentPlanDiscriminatorMappingStayOnLineVoice: oneOf: - $ref: '#/components/schemas/AzureVoice' - $ref: '#/components/schemas/CartesiaVoice' - $ref: '#/components/schemas/CustomVoice' - $ref: '#/components/schemas/DeepgramVoice' - $ref: '#/components/schemas/ElevenLabsVoice' - $ref: '#/components/schemas/HumeVoice' - $ref: '#/components/schemas/LMNTVoice' - $ref: '#/components/schemas/NeuphonicVoice' - $ref: '#/components/schemas/OpenAIVoice' - $ref: '#/components/schemas/PlayHTVoice' - $ref: '#/components/schemas/WellSaidVoice' - $ref: '#/components/schemas/RimeAIVoice' - $ref: '#/components/schemas/SmallestAIVoice' - $ref: '#/components/schemas/TavusVoice' - $ref: '#/components/schemas/VapiVoice' - $ref: '#/components/schemas/SesameVoice' - $ref: '#/components/schemas/InworldVoice' - $ref: '#/components/schemas/MinimaxVoice' description: >- This is the voice to use for the consent message. If not specified, inherits from the assistant's voice. Use a different voice for the consent message for a better user experience. title: CompliancePlanRecordingConsentPlanDiscriminatorMappingStayOnLineVoice CompliancePlanRecordingConsentPlanDiscriminatorMappingVerbalVoice: oneOf: - $ref: '#/components/schemas/AzureVoice' - $ref: '#/components/schemas/CartesiaVoice' - $ref: '#/components/schemas/CustomVoice' - $ref: '#/components/schemas/DeepgramVoice' - $ref: '#/components/schemas/ElevenLabsVoice' - $ref: '#/components/schemas/HumeVoice' - $ref: '#/components/schemas/LMNTVoice' - $ref: '#/components/schemas/NeuphonicVoice' - $ref: '#/components/schemas/OpenAIVoice' - $ref: '#/components/schemas/PlayHTVoice' - $ref: '#/components/schemas/WellSaidVoice' - $ref: '#/components/schemas/RimeAIVoice' - $ref: '#/components/schemas/SmallestAIVoice' - $ref: '#/components/schemas/TavusVoice' - $ref: '#/components/schemas/VapiVoice' - $ref: '#/components/schemas/SesameVoice' - $ref: '#/components/schemas/InworldVoice' - $ref: '#/components/schemas/MinimaxVoice' description: >- This is the voice to use for the consent message. If not specified, inherits from the assistant's voice. Use a different voice for the consent message for a better user experience. title: CompliancePlanRecordingConsentPlanDiscriminatorMappingVerbalVoice CompliancePlanRecordingConsentPlanDiscriminatorMappingVerbalDeclineTool: type: object properties: {} description: Tool to execute if user verbally declines recording consent title: CompliancePlanRecordingConsentPlanDiscriminatorMappingVerbalDeclineTool CompliancePlanRecordingConsentPlan: oneOf: - type: object properties: type: type: string enum: - stay-on-line description: 'Discriminator value: stay-on-line' message: type: string description: >- This is the message asking for consent to record the call. If the type is `stay-on-line`, the message should ask the user to hang up if they do not consent. If the type is `verbal`, the message should ask the user to verbally consent or decline. voice: $ref: >- #/components/schemas/CompliancePlanRecordingConsentPlanDiscriminatorMappingStayOnLineVoice description: >- This is the voice to use for the consent message. If not specified, inherits from the assistant's voice. Use a different voice for the consent message for a better user experience. waitSeconds: type: number format: double default: 3 description: >- Number of seconds to wait before transferring to the assistant if user stays on the call required: - type - message description: stay-on-line variant - type: object properties: type: type: string enum: - verbal description: 'Discriminator value: verbal' message: type: string description: >- This is the message asking for consent to record the call. If the type is `stay-on-line`, the message should ask the user to hang up if they do not consent. If the type is `verbal`, the message should ask the user to verbally consent or decline. voice: $ref: >- #/components/schemas/CompliancePlanRecordingConsentPlanDiscriminatorMappingVerbalVoice description: >- This is the voice to use for the consent message. If not specified, inherits from the assistant's voice. Use a different voice for the consent message for a better user experience. declineTool: $ref: >- #/components/schemas/CompliancePlanRecordingConsentPlanDiscriminatorMappingVerbalDeclineTool description: Tool to execute if user verbally declines recording consent declineToolId: type: string description: >- ID of existing tool to execute if user verbally declines recording consent required: - type - message description: verbal variant discriminator: propertyName: type title: CompliancePlanRecordingConsentPlan CompliancePlan: type: object properties: hipaaEnabled: type: boolean description: >- When this is enabled, logs, recordings, and transcriptions will be stored in HIPAA-compliant storage. Defaults to false. Only HIPAA-compliant providers will be available for LLM, Voice, and Transcriber respectively. This setting is only honored if the organization is on an Enterprise subscription or has purchased the HIPAA add-on. pciEnabled: type: boolean description: >- When this is enabled, the user will be restricted to use PCI-compliant providers, and no logs or transcripts are stored. At the end of the call, you will receive an end-of-call-report message to store on your server. Defaults to false. securityFilterPlan: $ref: '#/components/schemas/SecurityFilterPlan' description: >- This is the security filter plan for the assistant. It allows filtering of transcripts for security threats before sending to LLM. recordingConsentPlan: $ref: '#/components/schemas/CompliancePlanRecordingConsentPlan' title: CompliancePlan AssistantOverridesMetadata: type: object properties: {} description: This is for metadata you want to store on the assistant. title: AssistantOverridesMetadata SmartDenoisingPlan: type: object properties: enabled: type: boolean default: true description: Whether smart denoising using Krisp is enabled. title: SmartDenoisingPlan FourierDenoisingPlan: type: object properties: enabled: type: boolean default: false description: >- Whether Fourier denoising is enabled. Note that this is experimental and may not work as expected. mediaDetectionEnabled: type: boolean default: true description: >- Whether automatic media detection is enabled. When enabled, the filter will automatically detect consistent background TV/music/radio and switch to more aggressive filtering settings. Only applies when enabled is true. staticThreshold: type: number format: double default: -35 description: >- Static threshold in dB used as fallback when no baseline is established. baselineOffsetDb: type: number format: double default: -15 description: >- How far below the rolling baseline to filter audio, in dB. Lower values (e.g., -10) are more aggressive, higher values (e.g., -20) are more conservative. windowSizeMs: type: number format: double default: 3000 description: >- Rolling window size in milliseconds for calculating the audio baseline. Larger windows adapt more slowly but are more stable. baselinePercentile: type: number format: double default: 85 description: >- Percentile to use for baseline calculation (1-99). Higher percentiles (e.g., 85) focus on louder speech, lower percentiles (e.g., 50) include quieter speech. title: FourierDenoisingPlan BackgroundSpeechDenoisingPlan: type: object properties: smartDenoisingPlan: $ref: '#/components/schemas/SmartDenoisingPlan' description: Whether smart denoising using Krisp is enabled. fourierDenoisingPlan: $ref: '#/components/schemas/FourierDenoisingPlan' description: >- Whether Fourier denoising is enabled. Note that this is experimental and may not work as expected. This can be combined with smart denoising, and will be run afterwards. title: BackgroundSpeechDenoisingPlan StructuredDataPlanMessagesItems: type: object properties: {} title: StructuredDataPlanMessagesItems StructuredDataPlan: type: object properties: messages: type: array items: $ref: '#/components/schemas/StructuredDataPlanMessagesItems' description: >- These are the messages used to generate the structured data. @default: ``` [ { "role": "system", "content": "You are an expert data extractor. You will be given a transcript of a call. Extract structured data per the JSON Schema. DO NOT return anything except the structured data.\n\nJson Schema:\\n{{schema}}\n\nOnly respond with the JSON." }, { "role": "user", "content": "Here is the transcript:\n\n{{transcript}}\n\n. Here is the ended reason of the call:\n\n{{endedReason}}\n\n" } ]``` You can customize by providing any messages you want. Here are the template variables available: - {{transcript}}: the transcript of the call from `call.artifact.transcript`- {{systemPrompt}}: the system prompt of the call from `assistant.model.messages[type=system].content`- {{messages}}: the messages of the call from `assistant.model.messages`- {{schema}}: the schema of the structured data from `structuredDataPlan.schema`- {{endedReason}}: the ended reason of the call from `call.endedReason` enabled: type: boolean description: >- This determines whether structured data is generated and stored in `call.analysis.structuredData`. Defaults to false. Usage: - If you want to extract structured data, set this to true and provide a `schema`. @default false schema: $ref: '#/components/schemas/JsonSchema' description: >- This is the schema of the structured data. The output is stored in `call.analysis.structuredData`. Complete guide on JSON Schema can be found [here](https://ajv.js.org/json-schema.html#json-data-type). timeoutSeconds: type: number format: double description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.structuredData` will be empty. Usage: - To guarantee the structured data is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds title: StructuredDataPlan StructuredDataMultiPlan: type: object properties: key: type: string description: This is the key of the structured data plan in the catalog. plan: $ref: '#/components/schemas/StructuredDataPlan' description: This is an individual structured data plan in the catalog. required: - key - plan title: StructuredDataMultiPlan SuccessEvaluationPlanRubric: type: string enum: - NumericScale - DescriptiveScale - Checklist - Matrix - PercentageScale - LikertScale - AutomaticRubric - PassFail description: >- This enforces the rubric of the evaluation. The output is stored in `call.analysis.successEvaluation`. Options include: - 'NumericScale': A scale of 1 to 10. - 'DescriptiveScale': A scale of Excellent, Good, Fair, Poor. - 'Checklist': A checklist of criteria and their status. - 'Matrix': A grid that evaluates multiple criteria across different performance levels. - 'PercentageScale': A scale of 0% to 100%. - 'LikertScale': A scale of Strongly Agree, Agree, Neutral, Disagree, Strongly Disagree. - 'AutomaticRubric': Automatically break down evaluation into several criteria, each with its own score. - 'PassFail': A simple 'true' if call passed, 'false' if not. Default is 'PassFail'. title: SuccessEvaluationPlanRubric SuccessEvaluationPlanMessagesItems: type: object properties: {} title: SuccessEvaluationPlanMessagesItems SuccessEvaluationPlan: type: object properties: rubric: $ref: '#/components/schemas/SuccessEvaluationPlanRubric' description: >- This enforces the rubric of the evaluation. The output is stored in `call.analysis.successEvaluation`. Options include: - 'NumericScale': A scale of 1 to 10. - 'DescriptiveScale': A scale of Excellent, Good, Fair, Poor. - 'Checklist': A checklist of criteria and their status. - 'Matrix': A grid that evaluates multiple criteria across different performance levels. - 'PercentageScale': A scale of 0% to 100%. - 'LikertScale': A scale of Strongly Agree, Agree, Neutral, Disagree, Strongly Disagree. - 'AutomaticRubric': Automatically break down evaluation into several criteria, each with its own score. - 'PassFail': A simple 'true' if call passed, 'false' if not. Default is 'PassFail'. messages: type: array items: $ref: '#/components/schemas/SuccessEvaluationPlanMessagesItems' description: >- These are the messages used to generate the success evaluation. @default: ``` [ { "role": "system", "content": "You are an expert call evaluator. You will be given a transcript of a call and the system prompt of the AI participant. Determine if the call was successful based on the objectives inferred from the system prompt. DO NOT return anything except the result.\n\nRubric:\\n{{rubric}}\n\nOnly respond with the result." }, { "role": "user", "content": "Here is the transcript:\n\n{{transcript}}\n\n" }, { "role": "user", "content": "Here was the system prompt of the call:\n\n{{systemPrompt}}\n\n. Here is the ended reason of the call:\n\n{{endedReason}}\n\n" } ]``` You can customize by providing any messages you want. Here are the template variables available: - {{transcript}}: the transcript of the call from `call.artifact.transcript`- {{systemPrompt}}: the system prompt of the call from `assistant.model.messages[type=system].content`- {{messages}}: the messages of the call from `assistant.model.messages`- {{rubric}}: the rubric of the success evaluation from `successEvaluationPlan.rubric`- {{endedReason}}: the ended reason of the call from `call.endedReason` enabled: type: boolean description: >- This determines whether a success evaluation is generated and stored in `call.analysis.successEvaluation`. Defaults to true. Usage: - If you want to disable the success evaluation, set this to false. @default true timeoutSeconds: type: number format: double description: >- This is how long the request is tried before giving up. When request times out, `call.analysis.successEvaluation` will be empty. Usage: - To guarantee the success evaluation is generated, set this value high. Note, this will delay the end of call report in cases where model is slow to respond. @default 5 seconds title: SuccessEvaluationPlan AnalysisPlan: type: object properties: minMessagesThreshold: type: number format: double description: >- The minimum number of messages required to run the analysis plan. If the number of messages is less than this, analysis will be skipped. @default 2 summaryPlan: $ref: '#/components/schemas/SummaryPlan' description: >- This is the plan for generating the summary of the call. This outputs to `call.analysis.summary`. structuredDataPlan: $ref: '#/components/schemas/StructuredDataPlan' description: >- This is the plan for generating the structured data from the call. This outputs to `call.analysis.structuredData`. structuredDataMultiPlan: type: array items: $ref: '#/components/schemas/StructuredDataMultiPlan' description: >- This is an array of structured data plan catalogs. Each entry includes a `key` and a `plan` for generating the structured data from the call. This outputs to `call.analysis.structuredDataMulti`. successEvaluationPlan: $ref: '#/components/schemas/SuccessEvaluationPlan' description: >- This is the plan for generating the success evaluation of the call. This outputs to `call.analysis.successEvaluation`. outcomeIds: type: array items: type: string description: >- This is an array of outcome UUIDs to be calculated during analysis. The outcomes will be calculated and stored in `call.analysis.outcomes`. title: AnalysisPlan StartSpeakingPlanSmartEndpointingEnabled1: type: string enum: - livekit title: StartSpeakingPlanSmartEndpointingEnabled1 StartSpeakingPlanSmartEndpointingEnabled: oneOf: - type: boolean - $ref: '#/components/schemas/StartSpeakingPlanSmartEndpointingEnabled1' title: StartSpeakingPlanSmartEndpointingEnabled VapiSmartEndpointingPlanProvider: type: string enum: - vapi - livekit - custom-endpointing-model description: This is the provider for the smart endpointing plan. title: VapiSmartEndpointingPlanProvider VapiSmartEndpointingPlan: type: object properties: provider: $ref: '#/components/schemas/VapiSmartEndpointingPlanProvider' description: This is the provider for the smart endpointing plan. required: - provider title: VapiSmartEndpointingPlan LivekitSmartEndpointingPlanProvider: type: string enum: - vapi - livekit - custom-endpointing-model description: This is the provider for the smart endpointing plan. title: LivekitSmartEndpointingPlanProvider LivekitSmartEndpointingPlan: type: object properties: provider: $ref: '#/components/schemas/LivekitSmartEndpointingPlanProvider' description: This is the provider for the smart endpointing plan. waitFunction: type: string description: >- This expression describes how long the bot will wait to start speaking based on the likelihood that the user has reached an endpoint. This is a millisecond valued function. It maps probabilities (real numbers on [0,1]) to milliseconds that the bot should wait before speaking ([0, \infty]). Any negative values that are returned are set to zero (the bot can't start talking in the past). A probability of zero represents very high confidence that the caller has stopped speaking, and would like the bot to speak to them. A probability of one represents very high confidence that the caller is still speaking. Under the hood, this is parsed into a mathjs expression. Whatever you use to write your expression needs to be valid with respect to mathjs @default "20 + 500 * sqrt(x) + 2500 * x^3" required: - provider title: LivekitSmartEndpointingPlan CustomEndpointingModelSmartEndpointingPlanProvider: type: string enum: - vapi - livekit - custom-endpointing-model description: >- This is the provider for the smart endpointing plan. Use `custom-endpointing-model` for custom endpointing providers that are not natively supported. title: CustomEndpointingModelSmartEndpointingPlanProvider CustomEndpointingModelSmartEndpointingPlan: type: object properties: provider: $ref: >- #/components/schemas/CustomEndpointingModelSmartEndpointingPlanProvider description: >- This is the provider for the smart endpointing plan. Use `custom-endpointing-model` for custom endpointing providers that are not natively supported. server: $ref: '#/components/schemas/Server' description: >- This is where the endpointing request will be sent. If not provided, will be sent to `assistant.server`. If that does not exist either, will be sent to `org.server`. Request Example: POST https://{server.url} Content-Type: application/json { "message": { "type": "call.endpointing.request", "messages": [ { "role": "user", "message": "Hello, how are you?", "time": 1234567890, "secondsFromStart": 0 } ], ...other metadata about the call... } } Response Expected: { "timeoutSeconds": 0.5 } The timeout is the number of seconds to wait before considering the user's speech as finished. The endpointing timeout is automatically reset each time a new transcript is received (and another `call.endpointing.request` is sent). required: - provider title: CustomEndpointingModelSmartEndpointingPlan StartSpeakingPlanSmartEndpointingPlan: oneOf: - $ref: '#/components/schemas/VapiSmartEndpointingPlan' - $ref: '#/components/schemas/LivekitSmartEndpointingPlan' - $ref: '#/components/schemas/CustomEndpointingModelSmartEndpointingPlan' description: >- This is the plan for smart endpointing. Pick between Vapi smart endpointing, LiveKit, or custom endpointing model (or nothing). We strongly recommend using livekit endpointing when working in English. LiveKit endpointing is not supported in other languages, yet. If this is set, it will override and take precedence over `transcriptionEndpointingPlan`. This plan will still be overridden by any matching `customEndpointingRules`. If this is not set, the system will automatically use the transcriber's built-in endpointing capabilities if available. title: StartSpeakingPlanSmartEndpointingPlan AssistantCustomEndpointingRuleType: type: string enum: - assistant description: >- This endpointing rule is based on the last assistant message before customer started speaking. Flow: - Assistant speaks - Customer starts speaking - Customer transcription comes in - This rule is evaluated on the last assistant message - If a match is found based on `regex`, the endpointing timeout is set to `timeoutSeconds` Usage: - If you have yes/no questions in your use case like "are you interested in a loan?", you can set a shorter timeout. - If you have questions where the customer may pause to look up information like "what's my account number?", you can set a longer timeout. title: AssistantCustomEndpointingRuleType AssistantCustomEndpointingRule: type: object properties: type: $ref: '#/components/schemas/AssistantCustomEndpointingRuleType' description: >- This endpointing rule is based on the last assistant message before customer started speaking. Flow: - Assistant speaks - Customer starts speaking - Customer transcription comes in - This rule is evaluated on the last assistant message - If a match is found based on `regex`, the endpointing timeout is set to `timeoutSeconds` Usage: - If you have yes/no questions in your use case like "are you interested in a loan?", you can set a shorter timeout. - If you have questions where the customer may pause to look up information like "what's my account number?", you can set a longer timeout. regex: type: string description: >- This is the regex pattern to match. Note: - This works by using the `RegExp.test` method in Node.JS. Eg. `/hello/.test("hello there")` will return `true`. Hot tip: - In JavaScript, escape `\` when sending the regex pattern. Eg. `"hello\sthere"` will be sent over the wire as `"hellosthere"`. Send `"hello\\sthere"` instead. - `RegExp.test` does substring matching, so `/cat/.test("I love cats")` will return `true`. To do full string matching, send "^cat$". regexOptions: type: array items: $ref: '#/components/schemas/RegexOption' description: |- These are the options for the regex match. Defaults to all disabled. @default [] timeoutSeconds: type: number format: double description: This is the endpointing timeout in seconds, if the rule is matched. required: - type - regex - timeoutSeconds title: AssistantCustomEndpointingRule CustomerCustomEndpointingRuleType: type: string enum: - customer description: >- This endpointing rule is based on current customer message as they are speaking. Flow: - Assistant speaks - Customer starts speaking - Customer transcription comes in - This rule is evaluated on the current customer transcription - If a match is found based on `regex`, the endpointing timeout is set to `timeoutSeconds` Usage: - If you want to wait longer while customer is speaking numbers, you can set a longer timeout. title: CustomerCustomEndpointingRuleType CustomerCustomEndpointingRule: type: object properties: type: $ref: '#/components/schemas/CustomerCustomEndpointingRuleType' description: >- This endpointing rule is based on current customer message as they are speaking. Flow: - Assistant speaks - Customer starts speaking - Customer transcription comes in - This rule is evaluated on the current customer transcription - If a match is found based on `regex`, the endpointing timeout is set to `timeoutSeconds` Usage: - If you want to wait longer while customer is speaking numbers, you can set a longer timeout. regex: type: string description: >- This is the regex pattern to match. Note: - This works by using the `RegExp.test` method in Node.JS. Eg. `/hello/.test("hello there")` will return `true`. Hot tip: - In JavaScript, escape `\` when sending the regex pattern. Eg. `"hello\sthere"` will be sent over the wire as `"hellosthere"`. Send `"hello\\sthere"` instead. - `RegExp.test` does substring matching, so `/cat/.test("I love cats")` will return `true`. To do full string matching, send "^cat$". regexOptions: type: array items: $ref: '#/components/schemas/RegexOption' description: |- These are the options for the regex match. Defaults to all disabled. @default [] timeoutSeconds: type: number format: double description: This is the endpointing timeout in seconds, if the rule is matched. required: - type - regex - timeoutSeconds title: CustomerCustomEndpointingRule BothCustomEndpointingRuleType: type: string enum: - both description: >- This endpointing rule is based on both the last assistant message and the current customer message as they are speaking. Flow: - Assistant speaks - Customer starts speaking - Customer transcription comes in - This rule is evaluated on the last assistant message and the current customer transcription - If assistant message matches `assistantRegex` AND customer message matches `customerRegex`, the endpointing timeout is set to `timeoutSeconds` Usage: - If you want to wait longer while customer is speaking numbers, you can set a longer timeout. title: BothCustomEndpointingRuleType BothCustomEndpointingRule: type: object properties: type: $ref: '#/components/schemas/BothCustomEndpointingRuleType' description: >- This endpointing rule is based on both the last assistant message and the current customer message as they are speaking. Flow: - Assistant speaks - Customer starts speaking - Customer transcription comes in - This rule is evaluated on the last assistant message and the current customer transcription - If assistant message matches `assistantRegex` AND customer message matches `customerRegex`, the endpointing timeout is set to `timeoutSeconds` Usage: - If you want to wait longer while customer is speaking numbers, you can set a longer timeout. assistantRegex: type: string description: >- This is the regex pattern to match the assistant's message. Note: - This works by using the `RegExp.test` method in Node.JS. Eg. `/hello/.test("hello there")` will return `true`. Hot tip: - In JavaScript, escape `\` when sending the regex pattern. Eg. `"hello\sthere"` will be sent over the wire as `"hellosthere"`. Send `"hello\\sthere"` instead. - `RegExp.test` does substring matching, so `/cat/.test("I love cats")` will return `true`. To do full string matching, send "^cat$". assistantRegexOptions: type: array items: $ref: '#/components/schemas/RegexOption' description: >- These are the options for the assistant's message regex match. Defaults to all disabled. @default [] customerRegex: type: string customerRegexOptions: type: array items: $ref: '#/components/schemas/RegexOption' description: >- These are the options for the customer's message regex match. Defaults to all disabled. @default [] timeoutSeconds: type: number format: double description: This is the endpointing timeout in seconds, if the rule is matched. required: - type - assistantRegex - customerRegex - timeoutSeconds title: BothCustomEndpointingRule StartSpeakingPlanCustomEndpointingRulesItems: oneOf: - $ref: '#/components/schemas/AssistantCustomEndpointingRule' - $ref: '#/components/schemas/CustomerCustomEndpointingRule' - $ref: '#/components/schemas/BothCustomEndpointingRule' title: StartSpeakingPlanCustomEndpointingRulesItems TranscriptionEndpointingPlan: type: object properties: onPunctuationSeconds: type: number format: double description: >- The minimum number of seconds to wait after transcription ending with punctuation before sending a request to the model. Defaults to 0.1. This setting exists because the transcriber punctuates the transcription when it's more confident that customer has completed a thought. @default 0.1 onNoPunctuationSeconds: type: number format: double description: >- The minimum number of seconds to wait after transcription ending without punctuation before sending a request to the model. Defaults to 1.5. This setting exists to catch the cases where the transcriber was not confident enough to punctuate the transcription, but the customer is done and has been silent for a long time. @default 1.5 onNumberSeconds: type: number format: double description: >- The minimum number of seconds to wait after transcription ending with a number before sending a request to the model. Defaults to 0.4. This setting exists because the transcriber will sometimes punctuate the transcription ending with a number, even though the customer hasn't uttered the full number. This happens commonly for long numbers when the customer reads the number in chunks. @default 0.5 title: TranscriptionEndpointingPlan StartSpeakingPlan: type: object properties: waitSeconds: type: number format: double description: >- This is how long assistant waits before speaking. Defaults to 0.4. This is the minimum it will wait but if there is latency is the pipeline, this minimum will be exceeded. This is intended as a stopgap in case the pipeline is moving too fast. Example: - If model generates tokens and voice generates bytes within 100ms, the pipeline still waits 300ms before outputting speech. Usage: - If the customer is taking long pauses, set this to a higher value. - If the assistant is accidentally jumping in too much, set this to a higher value. @default 0.4 smartEndpointingEnabled: $ref: '#/components/schemas/StartSpeakingPlanSmartEndpointingEnabled' smartEndpointingPlan: $ref: '#/components/schemas/StartSpeakingPlanSmartEndpointingPlan' description: >- This is the plan for smart endpointing. Pick between Vapi smart endpointing, LiveKit, or custom endpointing model (or nothing). We strongly recommend using livekit endpointing when working in English. LiveKit endpointing is not supported in other languages, yet. If this is set, it will override and take precedence over `transcriptionEndpointingPlan`. This plan will still be overridden by any matching `customEndpointingRules`. If this is not set, the system will automatically use the transcriber's built-in endpointing capabilities if available. customEndpointingRules: type: array items: $ref: '#/components/schemas/StartSpeakingPlanCustomEndpointingRulesItems' description: >- These are the custom endpointing rules to set an endpointing timeout based on a regex on the customer's speech or the assistant's last message. Usage: - If you have yes/no questions like "are you interested in a loan?", you can set a shorter timeout. - If you have questions where the customer may pause to look up information like "what's my account number?", you can set a longer timeout. - If you want to wait longer while customer is enumerating a list of numbers, you can set a longer timeout. These rules have the highest precedence and will override both `smartEndpointingPlan` and `transcriptionEndpointingPlan` when a rule is matched. The rules are evaluated in order and the first one that matches will be used. Order of precedence for endpointing: 1. customEndpointingRules (if any match) 2. smartEndpointingPlan (if set) 3. transcriptionEndpointingPlan @default [] transcriptionEndpointingPlan: $ref: '#/components/schemas/TranscriptionEndpointingPlan' description: >- This determines how a customer speech is considered done (endpointing) using the transcription of customer's speech. Once an endpoint is triggered, the request is sent to `assistant.model`. Note: This plan is only used if `smartEndpointingPlan` is not set and transcriber does not have built-in endpointing capabilities. If both are provided, `smartEndpointingPlan` takes precedence. This plan will also be overridden by any matching `customEndpointingRules`. title: StartSpeakingPlan StopSpeakingPlan: type: object properties: numWords: type: number format: double description: >- This is the number of words that the customer has to say before the assistant will stop talking. Words like "stop", "actually", "no", etc. will always interrupt immediately regardless of this value. Words like "okay", "yeah", "right" will never interrupt. When set to 0, `voiceSeconds` is used in addition to the transcriptions to determine the customer has started speaking. Defaults to 0. @default 0 voiceSeconds: type: number format: double description: >- This is the seconds customer has to speak before the assistant stops talking. This uses the VAD (Voice Activity Detection) spike to determine if the customer has started speaking. Considerations: - A lower value might be more responsive but could potentially pick up non-speech sounds. - A higher value reduces false positives but might slightly delay the detection of speech onset. This is only used if `numWords` is set to 0. Defaults to 0.2 @default 0.2 backoffSeconds: type: number format: double description: >- This is the seconds to wait before the assistant will start talking again after being interrupted. Defaults to 1. @default 1 acknowledgementPhrases: type: array items: type: string description: >- These are the phrases that will never interrupt the assistant, even if numWords threshold is met. These are typically acknowledgement or backchanneling phrases. interruptionPhrases: type: array items: type: string description: >- These are the phrases that will always interrupt the assistant immediately, regardless of numWords. These are typically phrases indicating disagreement or desire to stop. title: StopSpeakingPlan MonitorPlan: type: object properties: listenEnabled: type: boolean description: >- This determines whether the assistant's calls allow live listening. Defaults to true. Fetch `call.monitor.listenUrl` to get the live listening URL. @default true listenAuthenticationEnabled: type: boolean description: >- This enables authentication on the `call.monitor.listenUrl`. If `listenAuthenticationEnabled` is `true`, the `call.monitor.listenUrl` will require an `Authorization: Bearer ` header. @default false controlEnabled: type: boolean description: >- This determines whether the assistant's calls allow live control. Defaults to true. Fetch `call.monitor.controlUrl` to get the live control URL. To use, send any control message via a POST request to `call.monitor.controlUrl`. Here are the types of controls supported: https://docs.vapi.ai/api-reference/messages/client-inbound-message @default true controlAuthenticationEnabled: type: boolean description: >- This enables authentication on the `call.monitor.controlUrl`. If `controlAuthenticationEnabled` is `true`, the `call.monitor.controlUrl` will require an `Authorization: Bearer ` header. @default false monitorIds: type: array items: type: string description: >- This the set of monitor ids that are attached to the assistant. The source of truth for the monitor ids is the assistant_monitor join table. This field can be used for transient assistants and to update assistants with new monitor ids. @default [] title: MonitorPlan KeypadInputPlanDelimiters: type: string enum: - '#' - '*' - '' description: |- This is the delimiter(s) that will be used to process the input. Can be '#', '*', or an empty array. title: KeypadInputPlanDelimiters KeypadInputPlan: type: object properties: enabled: type: boolean description: |- This keeps track of whether the user has enabled keypad input. By default, it is off. @default false timeoutSeconds: type: number format: double description: >- This is the time in seconds to wait before processing the input. If the input is not received within this time, the input will be ignored. If set to "off", the input will be processed when the user enters a delimiter or immediately if no delimiter is used. @default 2 delimiters: $ref: '#/components/schemas/KeypadInputPlanDelimiters' description: |- This is the delimiter(s) that will be used to process the input. Can be '#', '*', or an empty array. title: KeypadInputPlan AssistantOverrides: type: object properties: transcriber: $ref: '#/components/schemas/AssistantOverridesTranscriber' description: These are the options for the assistant's transcriber. model: $ref: '#/components/schemas/AssistantOverridesModel' description: These are the options for the assistant's LLM. voice: $ref: '#/components/schemas/AssistantOverridesVoice' description: These are the options for the assistant's voice. firstMessage: type: string description: >- This is the first message that the assistant will say. This can also be a URL to a containerized audio file (mp3, wav, etc.). If unspecified, assistant will wait for user to speak and use the model to respond once they speak. firstMessageInterruptionsEnabled: type: boolean default: false firstMessageMode: $ref: '#/components/schemas/AssistantOverridesFirstMessageMode' description: >- This is the mode for the first message. Default is 'assistant-speaks-first'. Use: - 'assistant-speaks-first' to have the assistant speak first. - 'assistant-waits-for-user' to have the assistant wait for the user to speak first. - 'assistant-speaks-first-with-model-generated-message' to have the assistant speak first with a message generated by the model based on the conversation state. (`assistant.model.messages` at call start, `call.messages` at squad transfer points). @default 'assistant-speaks-first' voicemailDetection: $ref: '#/components/schemas/AssistantOverridesVoicemailDetection' description: >- These are the settings to configure or disable voicemail detection. Alternatively, voicemail detection can be configured using the model.tools=[VoicemailTool]. By default, voicemail detection is disabled. clientMessages: $ref: '#/components/schemas/AssistantOverridesClientMessages' description: >- These are the messages that will be sent to your Client SDKs. Default is conversation-update,function-call,hang,model-output,speech-update,status-update,transfer-update,transcript,tool-calls,user-interrupted,voice-input,workflow.node.started,assistant.started. You can check the shape of the messages in ClientMessage schema. serverMessages: $ref: '#/components/schemas/AssistantOverridesServerMessages' description: >- These are the messages that will be sent to your Server URL. Default is conversation-update,end-of-call-report,function-call,hang,speech-update,status-update,tool-calls,transfer-destination-request,handoff-destination-request,user-interrupted,assistant.started. You can check the shape of the messages in ServerMessage schema. maxDurationSeconds: type: number format: double description: >- This is the maximum number of seconds that the call will last. When the call reaches this duration, it will be ended. @default 600 (10 minutes) backgroundSound: $ref: '#/components/schemas/AssistantOverridesBackgroundSound' description: >- This is the background sound in the call. Default for phone calls is 'office' and default for web calls is 'off'. You can also provide a custom sound by providing a URL to an audio file. modelOutputInMessagesEnabled: type: boolean description: >- This determines whether the model's output is used in conversation history rather than the transcription of assistant's speech. @default false transportConfigurations: type: array items: $ref: >- #/components/schemas/AssistantOverridesTransportConfigurationsItems description: >- These are the configurations to be passed to the transport providers of assistant's calls, like Twilio. You can store multiple configurations for different transport providers. For a call, only the configuration matching the call transport provider is used. observabilityPlan: $ref: '#/components/schemas/LangfuseObservabilityPlan' description: |- This is the plan for observability of assistant's calls. Currently, only Langfuse is supported. credentials: type: array items: $ref: '#/components/schemas/AssistantOverridesCredentialsItems' description: >- These are dynamic credentials that will be used for the assistant calls. By default, all the credentials are available for use in the call but you can supplement an additional credentials using this. Dynamic credentials override existing credentials. hooks: type: array items: $ref: '#/components/schemas/AssistantOverridesHooksItems' description: This is a set of actions that will be performed on certain events. tools:append: type: array items: $ref: '#/components/schemas/AssistantOverridesToolsAppendItems' variableValues: $ref: '#/components/schemas/AssistantOverridesVariableValues' description: >- These are values that will be used to replace the template variables in the assistant messages and other text-based fields. This uses LiquidJS syntax. https://liquidjs.com/tutorials/intro-to-liquid.html So for example, `{{ name }}` will be replaced with the value of `name` in `variableValues`. `{{"now" | date: "%b %d, %Y, %I:%M %p", "America/New_York"}}` will be replaced with the current date and time in New York. Some VAPI reserved defaults: - *customer* - the customer object name: type: string description: >- This is the name of the assistant. This is required when you want to transfer between assistants in a call. voicemailMessage: type: string description: >- This is the message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up. endCallMessage: type: string description: |- This is the message that the assistant will say if it ends the call. If unspecified, it will hang up without saying anything. endCallPhrases: type: array items: type: string description: >- This list contains phrases that, if spoken by the assistant, will trigger the call to be hung up. Case insensitive. compliancePlan: $ref: '#/components/schemas/CompliancePlan' metadata: $ref: '#/components/schemas/AssistantOverridesMetadata' description: This is for metadata you want to store on the assistant. backgroundSpeechDenoisingPlan: $ref: '#/components/schemas/BackgroundSpeechDenoisingPlan' description: >- This enables filtering of noise and background speech while the user is talking. Features: - Smart denoising using Krisp - Fourier denoising Smart denoising can be combined with or used independently of Fourier denoising. Order of precedence: - Smart denoising - Fourier denoising analysisPlan: $ref: '#/components/schemas/AnalysisPlan' description: >- This is the plan for analysis of assistant's calls. Stored in `call.analysis`. artifactPlan: $ref: '#/components/schemas/ArtifactPlan' description: >- This is the plan for artifacts generated during assistant's calls. Stored in `call.artifact`. startSpeakingPlan: $ref: '#/components/schemas/StartSpeakingPlan' description: >- This is the plan for when the assistant should start talking. You should configure this if you're running into these issues: - The assistant is too slow to start talking after the customer is done speaking. - The assistant is too fast to start talking after the customer is done speaking. - The assistant is so fast that it's actually interrupting the customer. stopSpeakingPlan: $ref: '#/components/schemas/StopSpeakingPlan' description: >- This is the plan for when assistant should stop talking on customer interruption. You should configure this if you're running into these issues: - The assistant is too slow to recognize customer's interruption. - The assistant is too fast to recognize customer's interruption. - The assistant is getting interrupted by phrases that are just acknowledgments. - The assistant is getting interrupted by background noises. - The assistant is not properly stopping -- it starts talking right after getting interrupted. monitorPlan: $ref: '#/components/schemas/MonitorPlan' description: >- This is the plan for real-time monitoring of the assistant's calls. Usage: - To enable live listening of the assistant's calls, set `monitorPlan.listenEnabled` to `true`. - To enable live control of the assistant's calls, set `monitorPlan.controlEnabled` to `true`. - To attach monitors to the assistant, set `monitorPlan.monitorIds` to the set of monitor ids. credentialIds: type: array items: type: string description: >- These are the credentials that will be used for the assistant calls. By default, all the credentials are available for use in the call but you can provide a subset using this. server: $ref: '#/components/schemas/Server' description: >- This is where Vapi will send webhooks. You can find all webhooks available along with their shape in ServerMessage schema. The order of precedence is: 1. assistant.server.url 2. phoneNumber.serverUrl 3. org.serverUrl keypadInputPlan: $ref: '#/components/schemas/KeypadInputPlan' title: AssistantOverrides HandoffDestinationAssistant: type: object properties: type: $ref: '#/components/schemas/HandoffDestinationAssistantType' contextEngineeringPlan: $ref: >- #/components/schemas/HandoffDestinationAssistantContextEngineeringPlan description: >- This is the plan for manipulating the message context before handing off the call to the next assistant. assistantName: type: string description: >- This is the assistant to transfer the call to. You must provide either assistantName or assistantId. assistantId: type: string description: >- This is the assistant id to transfer the call to. You must provide either assistantName or assistantId. assistant: $ref: '#/components/schemas/CreateAssistantDTO' description: >- This is a transient assistant to transfer the call to. You may provide a transient assistant in the response `handoff-destination-request` in a dynamic handoff. variableExtractionPlan: $ref: '#/components/schemas/VariableExtractionPlan' description: This is the variable extraction plan for the handoff tool. assistantOverrides: $ref: '#/components/schemas/AssistantOverrides' description: >- These are the assistant overrides to apply to the destination assistant. description: type: string description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. required: - type title: HandoffDestinationAssistant HandoffDestinationDynamicType: type: string enum: - dynamic title: HandoffDestinationDynamicType HandoffDestinationDynamic: type: object properties: type: $ref: '#/components/schemas/HandoffDestinationDynamicType' server: $ref: '#/components/schemas/Server' description: >- This is where Vapi will send the handoff-destination-request webhook in a dynamic handoff. The order of precedence is: 1. tool.server.url 2. assistant.server.url 3. phoneNumber.server.url 4. org.server.url description: type: string description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. required: - type title: HandoffDestinationDynamic HandoffDestinationSquadType: type: string enum: - squad title: HandoffDestinationSquadType HandoffDestinationSquadContextEngineeringPlan: oneOf: - $ref: '#/components/schemas/ContextEngineeringPlanLastNMessages' - $ref: '#/components/schemas/ContextEngineeringPlanNone' - $ref: '#/components/schemas/ContextEngineeringPlanAll' - $ref: '#/components/schemas/ContextEngineeringPlanUserAndAssistantMessages' description: >- This is the plan for manipulating the message context before handing off the call to the squad. title: HandoffDestinationSquadContextEngineeringPlan SquadMemberDtoAssistantDestinationsItems: oneOf: - $ref: '#/components/schemas/TransferDestinationAssistant' - $ref: '#/components/schemas/HandoffDestinationAssistant' title: SquadMemberDtoAssistantDestinationsItems SquadMemberDTO: type: object properties: assistantDestinations: type: array items: $ref: '#/components/schemas/SquadMemberDtoAssistantDestinationsItems' assistantId: type: - string - 'null' description: >- This is the assistant that will be used for the call. To use a transient assistant, use `assistant` instead. assistant: $ref: '#/components/schemas/CreateAssistantDTO' description: >- This is the assistant that will be used for the call. To use an existing assistant, use `assistantId` instead. assistantOverrides: $ref: '#/components/schemas/AssistantOverrides' description: >- This can be used to override the assistant's settings and provide values for it's template variables. title: SquadMemberDTO CreateSquadDTO: type: object properties: name: type: string description: This is the name of the squad. members: type: array items: $ref: '#/components/schemas/SquadMemberDTO' description: |- This is the list of assistants that make up the squad. The call will start with the first assistant in the list. membersOverrides: $ref: '#/components/schemas/AssistantOverrides' description: >- This can be used to override all the assistants' settings and provide values for their template variables. Both `membersOverrides` and `members[n].assistantOverrides` can be used together. First, `members[n].assistantOverrides` is applied. Then, `membersOverrides` is applied as a global override. required: - members title: CreateSquadDTO HandoffDestinationSquad: type: object properties: type: $ref: '#/components/schemas/HandoffDestinationSquadType' contextEngineeringPlan: $ref: '#/components/schemas/HandoffDestinationSquadContextEngineeringPlan' description: >- This is the plan for manipulating the message context before handing off the call to the squad. squadId: type: string description: This is the squad id to transfer the call to. squad: $ref: '#/components/schemas/CreateSquadDTO' description: This is a transient squad to transfer the call to. entryAssistantName: type: string description: >- This is the name of the entry assistant to start with when handing off to the squad. If not provided, the first member of the squad will be used. variableExtractionPlan: $ref: '#/components/schemas/VariableExtractionPlan' description: This is the variable extraction plan for the handoff tool. squadOverrides: $ref: '#/components/schemas/AssistantOverrides' description: |- These are the overrides to apply to the squad configuration. Maps to squad-level membersOverrides. description: type: string description: >- This is the description of the destination, used by the AI to choose when and how to transfer the call. required: - type title: HandoffDestinationSquad ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingHandoffDestinationsItems: oneOf: - $ref: '#/components/schemas/HandoffDestinationAssistant' - $ref: '#/components/schemas/HandoffDestinationDynamic' - $ref: '#/components/schemas/HandoffDestinationSquad' title: >- ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingHandoffDestinationsItems CreateHandoffToolDTO: type: object properties: messages: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingHandoffMessagesItems description: >- These are the messages that will be spoken to the user as the tool is running. For some tools, this is auto-filled based on special fields like `tool.destinations`. For others like the function tool, these can be custom configured. defaultResult: type: string description: >- This is the default local tool result message used when no runtime handoff result override is returned. destinations: type: array items: $ref: >- #/components/schemas/ToolPostRequestBodyContentApplicationJsonSchemaDiscriminatorMappingHandoffDestinationsItems description: >- These are the destinations that the call can be handed off to. Usage: 1. Single destination Use `assistantId` to handoff the call to a saved assistant, or `assistantName` to handoff the call to an assistant in the same squad. ```json { "tools": [ { "type": "handoff", "destinations": [ { "type": "assistant", "assistantId": "assistant-123", // or "assistantName": "Assistant123" "description": "customer wants to be handed off to assistant-123", "contextEngineeringPlan": { "type": "all" } } ], } ] } ``` 2. Multiple destinations 2.1. Multiple Tools, Each With One Destination (OpenAI recommended) ```json { "tools": [ { "type": "handoff", "destinations": [ { "type": "assistant", "assistantId": "assistant-123", "description": "customer wants to be handed off to assistant-123", "contextEngineeringPlan": { "type": "all" } }, ], }, { "type": "handoff", "destinations": [ { "type": "assistant", "assistantId": "assistant-456", "description": "customer wants to be handed off to assistant-456", "contextEngineeringPlan": { "type": "all" } } ], } ] } ``` 2.2. One Tool, Multiple Destinations (Anthropic recommended) ```json { "tools": [ { "type": "handoff", "destinations": [ { "type": "assistant", "assistantId": "assistant-123", "description": "customer wants to be handed off to assistant-123", "contextEngineeringPlan": { "type": "all" } }, { "type": "assistant", "assistantId": "assistant-456", "description": "customer wants to be handed off to assistant-456", "contextEngineeringPlan": { "type": "all" } } ], } ] } ``` 3. Dynamic destination 3.1 To determine the destination dynamically, supply a `dynamic` handoff destination type and a `server` object. VAPI will send a handoff-destination-request webhook to the `server.url`. The response from the server will be used as the destination (if valid). ```json { "tools": [ { "type": "handoff", "destinations": [ { "type": "dynamic", "server": { "url": "https://example.com" } } ], } ] } ``` 3.2. To pass custom parameters to the server, you can use the `function` object. ```json { "tools": [ { "type": "handoff", "destinations": [ { "type": "dynamic", "server": { "url": "https://example.com" }, } ], "function": { "name": "handoff", "description": "Call this function when the customer is ready to be handed off to the next assistant", "parameters": { "type": "object", "properties": { "destination": { "type": "string", "description": "Use dynamic when customer is ready to be handed off to the next assistant", "enum": ["dynamic"] }, "customerAreaCode": { "type": "number", "description": "Area code of the customer" }, "customerIntent": { "type": "string", "enum": ["new-customer", "existing-customer"], "description": "Use new-customer when customer is a new customer, existing-customer when customer is an existing customer" }, "customerSentiment": { "type": "string", "enum": ["positive", "negative", "neutral"], "description": "Use positive when customer is happy, negative when customer is unhappy, neutral when customer is neutral" } } } } } ] } ``` The properties `customerAreaCode`, `customerIntent`, and `customerSentiment` will be passed to the server in the webhook request body. function: $ref: '#/components/schemas/OpenAIFunction' description: >- This is the optional function definition that will be passed to the LLM. If this is not defined, we will construct this based on the other properties. For example, given the following tools definition: ```json { "tools": [ { "type": "handoff", "destinations": [ { "type": "assistant", "assistantId": "assistant-123", "description": "customer wants to be handed off to assistant-123", "contextEngineeringPlan": { "type": "all" } }, { "type": "assistant", "assistantId": "assistant-456", "description": "customer wants to be handed off to assistant-456", "contextEngineeringPlan": { "type": "all" } } ], } ] } ``` We will construct the following function definition: ```json { "function": { "name": "handoff_to_assistant-123", "description": " Use this function to handoff the call to the next assistant. Only use it when instructions explicitly ask you to use the handoff_to_assistant function. DO NOT call this function unless you are instructed to do so. Here are the destinations you can handoff the call to: 1. assistant-123. When: customer wants to be handed off to assistant-123 2. assistant-456. When: customer wants to be handed off to assistant-456 ", "parameters": { "type": "object", "properties": { "destination": { "type": "string", "description": "Options: assistant-123 (customer wants to be handed off to assistant-123), assistant-456 (customer wants to be handed off to assistant-456)", "enum": ["assistant-123", "assistant-456"] }, }, "required": ["destination"] } } } ``` To override this function, please provide an OpenAI function definition and refer to it in the system prompt. You may override parts of the function definition (i.e. you may only want to change the function name for your prompt). If you choose to override the function parameters, it must include `destination` as a required parameter, and it must evaluate to either an assistantId, assistantName, or a the string literal `dynamic`. To pass custom parameters to the server in a dynamic handoff, you can use the function parameters, with `dynamic` as the destination. ```json { "function": { "name": "dynamic_handoff", "description": " Call this function when the customer is ready to be handed off to the next assistant ", "parameters": { "type": "object", "properties": { "destination": { "type": "string", "enum": ["dynamic"] }, "customerAreaCode": { "type": "number", "description": "Area code of the customer" }, "customerIntent": { "type": "string", "enum": ["new-customer", "existing-customer"], "description": "Use new-customer when customer is a new customer, existing-customer when customer is an existing customer" }, "customerSentiment": { "type": "string", "enum": ["positive", "negative", "neutral"], "description": "Use positive when customer is happy, negative when customer is unhappy, neutral when customer is neutral" } }, "required": ["destination", "customerAreaCode", "customerIntent", "customerSentiment"] } } } ``` rejectionPlan: $ref: '#/components/schemas/ToolRejectionPlan' description: >- This is the plan to reject a tool call based on the conversation state. // Example 1: Reject endCall if user didn't say goodbye ```json { conditions: [{ type: 'regex', regex: '(?i)\\b(bye|goodbye|farewell|see you later|take care)\\b', target: { position: -1, role: 'user' }, negate: true // Reject if pattern does NOT match }] } ``` // Example 2: Reject transfer if user is actually asking a question ```json { conditions: [{ type: 'regex', regex: '\\?', target: { position: -1, role: 'user' } }] } ``` // Example 3: Reject transfer if user didn't mention transfer recently ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 5 %} {% assign userMessages = recentMessages | where: 'role', 'user' %} {% assign mentioned = false %} {% for msg in userMessages %} {% if msg.content contains 'transfer' or msg.content contains 'connect' or msg.content contains 'speak to' %} {% assign mentioned = true %} {% break %} {% endif %} {% endfor %} {% if mentioned %} false {% else %} true {% endif %}` }] } ``` // Example 4: Reject endCall if the bot is looping and trying to exit ```json { conditions: [{ type: 'liquid', liquid: `{% assign recentMessages = messages | last: 6 %} {% assign userMessages = recentMessages | where: 'role', 'user' | reverse %} {% if userMessages.size < 3 %} false {% else %} {% assign msg1 = userMessages[0].content | downcase %} {% assign msg2 = userMessages[1].content | downcase %} {% assign msg3 = userMessages[2].content | downcase %} {% comment %} Check for repetitive messages {% endcomment %} {% if msg1 == msg2 or msg1 == msg3 or msg2 == msg3 %} true {% comment %} Check for common loop phrases {% endcomment %} {% elsif msg1 contains 'cool thanks' or msg2 contains 'cool thanks' or msg3 contains 'cool thanks' %} true {% elsif msg1 contains 'okay thanks' or msg2 contains 'okay thanks' or msg3 contains 'okay thanks' %} true {% elsif msg1 contains 'got it' or msg2 contains 'got it' or msg3 contains 'got it' %} true {% else %} false {% endif %} {% endif %}` }] } ``` title: CreateHandoffToolDTO AnthropicModelToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: AnthropicModelToolsItems AnthropicModelKnowledgeBase: oneOf: - $ref: '#/components/schemas/CreateCustomKnowledgeBaseDTO' description: These are the options for the knowledge base. title: AnthropicModelKnowledgeBase AnthropicModelModel: type: string enum: - claude-3-opus-20240229 - claude-3-sonnet-20240229 - claude-3-haiku-20240307 - claude-3-5-sonnet-20240620 - claude-3-5-sonnet-20241022 - claude-3-5-haiku-20241022 - claude-3-7-sonnet-20250219 - claude-opus-4-20250514 - claude-opus-4-5-20251101 - claude-opus-4-6 - claude-sonnet-4-20250514 - claude-sonnet-4-5-20250929 - claude-sonnet-4-6 - claude-haiku-4-5-20251001 description: The specific Anthropic/Claude model that will be used. title: AnthropicModelModel AnthropicModelProvider: type: string enum: - anthropic description: The provider identifier for Anthropic. title: AnthropicModelProvider AnthropicModel: type: object properties: messages: type: array items: $ref: '#/components/schemas/OpenAIMessage' description: This is the starting state for the conversation. tools: type: array items: $ref: '#/components/schemas/AnthropicModelToolsItems' description: >- These are the tools that the assistant can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the assistant can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. knowledgeBase: $ref: '#/components/schemas/AnthropicModelKnowledgeBase' description: These are the options for the knowledge base. model: $ref: '#/components/schemas/AnthropicModelModel' description: The specific Anthropic/Claude model that will be used. provider: $ref: '#/components/schemas/AnthropicModelProvider' description: The provider identifier for Anthropic. thinking: $ref: '#/components/schemas/AnthropicThinkingConfig' description: |- Optional configuration for Anthropic's thinking feature. Only applicable for claude-3-7-sonnet-20250219 model. If provided, maxTokens must be greater than thinking.budgetTokens. temperature: type: number format: double description: >- This is the temperature that will be used for calls. Default is 0 to leverage caching for lower latency. maxTokens: type: number format: double description: >- This is the max number of tokens that the assistant will be allowed to generate in each turn of the conversation. Default is 250. emotionRecognitionEnabled: type: boolean description: >- This determines whether we detect user's emotion while they speak and send it as an additional info to model. Default `false` because the model is usually are good at understanding the user's emotion from text. @default false numFastTurns: type: number format: double description: >- This sets how many turns at the start of the conversation to use a smaller, faster model from the same provider before switching to the primary model. Example, gpt-3.5-turbo if provider is openai. Default is 0. @default 0 required: - model - provider title: AnthropicModel CreateAssistantDtoModel: oneOf: - $ref: '#/components/schemas/AnthropicModel' - $ref: '#/components/schemas/AnthropicBedrockModel' - $ref: '#/components/schemas/AnyscaleModel' - $ref: '#/components/schemas/CerebrasModel' - $ref: '#/components/schemas/CustomLLMModel' - $ref: '#/components/schemas/DeepInfraModel' - $ref: '#/components/schemas/DeepSeekModel' - $ref: '#/components/schemas/GoogleModel' - $ref: '#/components/schemas/GroqModel' - $ref: '#/components/schemas/InflectionAIModel' - $ref: '#/components/schemas/MinimaxLLMModel' - $ref: '#/components/schemas/OpenAIModel' - $ref: '#/components/schemas/OpenRouterModel' - $ref: '#/components/schemas/PerplexityAIModel' - $ref: '#/components/schemas/TogetherAIModel' - $ref: '#/components/schemas/XaiModel' description: These are the options for the assistant's LLM. title: CreateAssistantDtoModel CreateAssistantDtoVoice: oneOf: - $ref: '#/components/schemas/AzureVoice' - $ref: '#/components/schemas/CartesiaVoice' - $ref: '#/components/schemas/CustomVoice' - $ref: '#/components/schemas/DeepgramVoice' - $ref: '#/components/schemas/ElevenLabsVoice' - $ref: '#/components/schemas/HumeVoice' - $ref: '#/components/schemas/LMNTVoice' - $ref: '#/components/schemas/NeuphonicVoice' - $ref: '#/components/schemas/OpenAIVoice' - $ref: '#/components/schemas/PlayHTVoice' - $ref: '#/components/schemas/WellSaidVoice' - $ref: '#/components/schemas/RimeAIVoice' - $ref: '#/components/schemas/SmallestAIVoice' - $ref: '#/components/schemas/TavusVoice' - $ref: '#/components/schemas/VapiVoice' - $ref: '#/components/schemas/SesameVoice' - $ref: '#/components/schemas/InworldVoice' - $ref: '#/components/schemas/MinimaxVoice' description: These are the options for the assistant's voice. title: CreateAssistantDtoVoice CreateAssistantDtoFirstMessageMode: type: string enum: - assistant-speaks-first - assistant-speaks-first-with-model-generated-message - assistant-waits-for-user description: >- This is the mode for the first message. Default is 'assistant-speaks-first'. Use: - 'assistant-speaks-first' to have the assistant speak first. - 'assistant-waits-for-user' to have the assistant wait for the user to speak first. - 'assistant-speaks-first-with-model-generated-message' to have the assistant speak first with a message generated by the model based on the conversation state. (`assistant.model.messages` at call start, `call.messages` at squad transfer points). @default 'assistant-speaks-first' title: CreateAssistantDtoFirstMessageMode CreateAssistantDtoVoicemailDetection0: type: string enum: - 'off' title: CreateAssistantDtoVoicemailDetection0 CreateAssistantDtoVoicemailDetection: oneOf: - $ref: '#/components/schemas/CreateAssistantDtoVoicemailDetection0' - $ref: '#/components/schemas/GoogleVoicemailDetectionPlan' - $ref: '#/components/schemas/OpenAIVoicemailDetectionPlan' - $ref: '#/components/schemas/TwilioVoicemailDetectionPlan' - $ref: '#/components/schemas/VapiVoicemailDetectionPlan' description: >- These are the settings to configure or disable voicemail detection. Alternatively, voicemail detection can be configured using the model.tools=[VoicemailTool]. By default, voicemail detection is disabled. title: CreateAssistantDtoVoicemailDetection CreateAssistantDtoClientMessages: type: string enum: - conversation-update - assistant.speechStarted - function-call - function-call-result - hang - language-changed - metadata - model-output - speech-update - status-update - transcript - tool-calls - tool-calls-result - tool.completed - transfer-update - user-interrupted - voice-input - workflow.node.started - assistant.started description: >- These are the messages that will be sent to your Client SDKs. Default is conversation-update,function-call,hang,model-output,speech-update,status-update,transfer-update,transcript,tool-calls,user-interrupted,voice-input,workflow.node.started,assistant.started. You can check the shape of the messages in ClientMessage schema. title: CreateAssistantDtoClientMessages CreateAssistantDtoServerMessages: type: string enum: - assistant.started - assistant.speechStarted - conversation-update - end-of-call-report - function-call - hang - language-changed - language-change-detected - model-output - phone-call-control - speech-update - status-update - transcript - transcript[transcriptType="final"] - tool-calls - transfer-destination-request - handoff-destination-request - transfer-update - user-interrupted - voice-input - chat.created - chat.deleted - session.created - session.updated - session.deleted - call.deleted - call.delete.failed description: >- These are the messages that will be sent to your Server URL. Default is conversation-update,end-of-call-report,function-call,hang,speech-update,status-update,tool-calls,transfer-destination-request,handoff-destination-request,user-interrupted,assistant.started. You can check the shape of the messages in ServerMessage schema. title: CreateAssistantDtoServerMessages CreateAssistantDtoBackgroundSound0: type: string enum: - 'off' - office title: CreateAssistantDtoBackgroundSound0 CreateAssistantDtoBackgroundSound: oneOf: - $ref: '#/components/schemas/CreateAssistantDtoBackgroundSound0' - type: string format: uri description: >- This is the background sound in the call. Default for phone calls is 'office' and default for web calls is 'off'. You can also provide a custom sound by providing a URL to an audio file. title: CreateAssistantDtoBackgroundSound CreateAssistantDtoTransportConfigurationsItems: oneOf: - $ref: '#/components/schemas/TransportConfigurationTwilio' title: CreateAssistantDtoTransportConfigurationsItems CreateAssistantDtoCredentialsItems: oneOf: - type: object properties: provider: type: string enum: - 11labs description: 'Discriminator value: 11labs' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateElevenLabsCredentialDTO variant - type: object properties: provider: type: string enum: - anthropic description: 'Discriminator value: anthropic' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateAnthropicCredentialDTO variant - type: object properties: provider: type: string enum: - anthropic-bedrock description: 'Discriminator value: anthropic-bedrock' region: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockRegion description: AWS region where Bedrock is configured. authenticationPlan: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockAuthenticationPlan description: >- Authentication method - either direct IAM credentials or cross-account role assumption. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - region - authenticationPlan description: anthropic-bedrock variant - type: object properties: provider: type: string enum: - anyscale description: 'Discriminator value: anyscale' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateAnyscaleCredentialDTO variant - type: object properties: provider: type: string enum: - assembly-ai description: 'Discriminator value: assembly-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateAssemblyAICredentialDTO variant - type: object properties: provider: type: string enum: - azure-openai description: 'Discriminator value: azure-openai' region: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiRegion models: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiModels openAIKey: type: string description: This is not returned in the API. ocpApimSubscriptionKey: type: string description: This is not returned in the API. openAIEndpoint: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - region - models - openAIKey - openAIEndpoint description: CreateAzureOpenAICredentialDTO variant - type: object properties: provider: type: string enum: - azure description: 'Discriminator value: azure' service: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureService description: This is the service being used in Azure. region: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureRegion description: This is the region of the Azure resource. apiKey: type: string description: This is not returned in the API. fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/AzureBlobStorageBucketPlan' description: >- This is the bucket plan that can be provided to store call artifacts in Azure Blob Storage. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - service description: CreateAzureCredentialDTO variant - type: object properties: provider: type: string enum: - byo-sip-trunk description: 'Discriminator value: byo-sip-trunk' gateways: type: array items: $ref: '#/components/schemas/SipTrunkGateway' description: This is the list of SIP trunk's gateways. outboundAuthenticationPlan: $ref: '#/components/schemas/SipTrunkOutboundAuthenticationPlan' description: >- This can be used to configure the outbound authentication if required by the SIP trunk. outboundLeadingPlusEnabled: type: boolean description: >- This ensures the outbound origination attempts have a leading plus. Defaults to false to match conventional telecom behavior. Usage: - Vonage/Twilio requires leading plus for all outbound calls. Set this to true. @default false techPrefix: type: string description: >- This can be used to configure the tech prefix on outbound calls. This is an advanced property. sipDiversionHeader: type: string description: >- This can be used to enable the SIP diversion header for authenticating the calling number if the SIP trunk supports it. This is an advanced property. sbcConfiguration: $ref: '#/components/schemas/SbcConfiguration' description: >- This is an advanced configuration for enterprise deployments. This uses the onprem SBC to trunk into the SIP trunk's `gateways`, rather than the managed SBC provided by Vapi. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - gateways description: CreateByoSipTrunkCredentialDTO variant - type: object properties: provider: type: string enum: - cartesia description: 'Discriminator value: cartesia' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateCartesiaCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateCerebrasCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateCerebrasCredentialDTO variant - type: object properties: provider: type: string enum: - cloudflare description: 'Discriminator value: cloudflare' accountId: type: string description: Cloudflare Account Id. apiKey: type: string description: Cloudflare API Key / Token. accountEmail: type: string description: Cloudflare Account Email. fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/CloudflareR2BucketPlan' description: >- This is the bucket plan that can be provided to store call artifacts in R2 name: type: string description: This is the name of credential. This is just for your reference. required: - provider description: CreateCloudflareCredentialDTO variant - type: object properties: provider: type: string enum: - custom-llm description: 'Discriminator value: custom-llm' apiKey: type: string description: This is not returned in the API. authenticationPlan: $ref: '#/components/schemas/OAuth2AuthenticationPlan' description: >- This is the authentication plan. Currently supports OAuth2 RFC 6749. To use Bearer authentication, use apiKey name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateCustomLLMCredentialDTO variant - type: object properties: provider: type: string enum: - deepgram description: 'Discriminator value: deepgram' apiKey: type: string description: This is not returned in the API. apiUrl: type: string description: >- This can be used to point to an onprem Deepgram instance. Defaults to api.deepgram.com. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateDeepgramCredentialDTO variant - type: object properties: provider: type: string enum: - deepinfra description: 'Discriminator value: deepinfra' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateDeepInfraCredentialDTO variant - type: object properties: provider: type: string enum: - deep-seek description: 'Discriminator value: deep-seek' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateDeepSeekCredentialDTO variant - type: object properties: provider: type: string enum: - gcp description: 'Discriminator value: gcp' fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. gcpKey: $ref: '#/components/schemas/GcpKey' description: >- This is the GCP key. This is the JSON that can be generated in the Google Cloud Console at https://console.cloud.google.com/iam-admin/serviceaccounts/details//keys. The schema is identical to the JSON that GCP outputs. region: type: string description: This is the region of the GCP resource. bucketPlan: $ref: '#/components/schemas/BucketPlan' name: type: string description: This is the name of credential. This is just for your reference. required: - provider - gcpKey description: CreateGcpCredentialDTO variant - type: object properties: provider: type: string enum: - gladia description: 'Discriminator value: gladia' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGladiaCredentialDTO variant - type: object properties: provider: type: string enum: - gohighlevel description: 'Discriminator value: gohighlevel' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGoHighLevelCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateGoogleCredentialDtoProvider' description: >- This is the key for Gemini in Google AI Studio. Get it from here: https://aistudio.google.com/app/apikey apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGoogleCredentialDTO variant - type: object properties: provider: type: string enum: - groq description: 'Discriminator value: groq' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGroqCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateInflectionAiCredentialDtoProvider' description: >- This is the api key for Pi in InflectionAI's console. Get it from here: https://developers.inflection.ai/keys, billing will need to be setup apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateInflectionAICredentialDTO variant - type: object properties: provider: type: string enum: - langfuse description: 'Discriminator value: langfuse' publicKey: type: string description: 'The public key for Langfuse project. Eg: pk-lf-...' apiKey: type: string description: >- The secret key for Langfuse project. Eg: sk-lf-... .This is not returned in the API. apiUrl: type: string description: >- The host URL for Langfuse project. Eg: https://cloud.langfuse.com name: type: string description: This is the name of credential. This is just for your reference. required: - provider - publicKey - apiKey - apiUrl description: CreateLangfuseCredentialDTO variant - type: object properties: provider: type: string enum: - lmnt description: 'Discriminator value: lmnt' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateLmntCredentialDTO variant - type: object properties: provider: type: string enum: - make description: 'Discriminator value: make' teamId: type: string description: Team ID region: type: string description: 'Region of your application. For example: eu1, eu2, us1, us2' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - teamId - region - apiKey description: CreateMakeCredentialDTO variant - type: object properties: provider: type: string enum: - openai description: 'Discriminator value: openai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateOpenAICredentialDTO variant - type: object properties: provider: type: string enum: - openrouter description: 'Discriminator value: openrouter' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateOpenRouterCredentialDTO variant - type: object properties: provider: type: string enum: - perplexity-ai description: 'Discriminator value: perplexity-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreatePerplexityAICredentialDTO variant - type: object properties: provider: type: string enum: - playht description: 'Discriminator value: playht' apiKey: type: string description: This is not returned in the API. userId: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey - userId description: CreatePlayHTCredentialDTO variant - type: object properties: provider: type: string enum: - rime-ai description: 'Discriminator value: rime-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateRimeAICredentialDTO variant - type: object properties: provider: type: string enum: - runpod description: 'Discriminator value: runpod' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateRunpodCredentialDTO variant - type: object properties: provider: type: string enum: - s3 description: 'Discriminator value: s3' awsAccessKeyId: type: string description: AWS access key ID. awsSecretAccessKey: type: string description: AWS access key secret. This is not returned in the API. region: type: string description: AWS region in which the S3 bucket is located. s3BucketName: type: string description: AWS S3 bucket name. s3PathPrefix: type: string description: The path prefix for the uploaded recording. Ex. "recordings/" fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - awsAccessKeyId - awsSecretAccessKey - region - s3BucketName - s3PathPrefix description: CreateS3CredentialDTO variant - type: object properties: provider: type: string enum: - supabase description: 'Discriminator value: supabase' fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/SupabaseBucketPlan' name: type: string description: This is the name of credential. This is just for your reference. required: - provider description: CreateSupabaseCredentialDTO variant - type: object properties: provider: type: string enum: - smallest-ai description: 'Discriminator value: smallest-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateSmallestAICredentialDTO variant - type: object properties: provider: type: string enum: - tavus description: 'Discriminator value: tavus' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateTavusCredentialDTO variant - type: object properties: provider: type: string enum: - together-ai description: 'Discriminator value: together-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateTogetherAICredentialDTO variant - type: object properties: provider: type: string enum: - twilio description: 'Discriminator value: twilio' authToken: type: string description: This is not returned in the API. apiKey: type: string description: This is not returned in the API. apiSecret: type: string description: This is not returned in the API. accountSid: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - accountSid description: CreateTwilioCredentialDTO variant - type: object properties: provider: type: string enum: - vonage description: 'Discriminator value: vonage' apiSecret: type: string description: This is not returned in the API. apiKey: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiSecret - apiKey description: CreateVonageCredentialDTO variant - type: object properties: provider: type: string enum: - webhook description: 'Discriminator value: webhook' authenticationPlan: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingWebhookAuthenticationPlan description: >- This is the authentication plan. Supports OAuth2 RFC 6749, HMAC signing, and Bearer authentication. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authenticationPlan description: CreateWebhookCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateCustomCredentialDtoProvider' authenticationPlan: $ref: '#/components/schemas/CreateCustomCredentialDtoAuthenticationPlan' description: >- This is the authentication plan. Supports OAuth2 RFC 6749, HMAC signing, and Bearer authentication. encryptionPlan: $ref: '#/components/schemas/PublicKeyEncryptionPlan' description: >- This is the encryption plan for encrypting sensitive data. Currently supports public-key encryption. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authenticationPlan description: custom-credential variant - type: object properties: provider: type: string enum: - xai description: 'Discriminator value: xai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateXAiCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateNeuphonicCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateNeuphonicCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateHumeCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateHumeCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateMistralCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateMistralCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateSpeechmaticsCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateSpeechmaticsCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateSonioxCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: soniox variant - type: object properties: provider: $ref: '#/components/schemas/CreateTrieveCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateTrieveCredentialDTO variant - type: object properties: provider: type: string enum: - google.calendar.oauth2-client description: 'Discriminator value: google.calendar.oauth2-client' name: type: string description: This is the name of credential. This is just for your reference. required: - provider description: CreateGoogleCalendarOAuth2ClientCredentialDTO variant - type: object properties: provider: type: string enum: - google.calendar.oauth2-authorization description: 'Discriminator value: google.calendar.oauth2-authorization' authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authorizationId description: CreateGoogleCalendarOAuth2AuthorizationCredentialDTO variant - type: object properties: provider: type: string enum: - google.sheets.oauth2-authorization description: 'Discriminator value: google.sheets.oauth2-authorization' authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authorizationId description: CreateGoogleSheetsOAuth2AuthorizationCredentialDTO variant - type: object properties: provider: type: string enum: - slack.oauth2-authorization description: 'Discriminator value: slack.oauth2-authorization' authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authorizationId description: CreateSlackOAuth2AuthorizationCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateGoHighLevelMcpCredentialDtoProvider' authenticationSession: $ref: '#/components/schemas/Oauth2AuthenticationSession' description: This is the authentication session for the credential. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authenticationSession description: CreateGoHighLevelMCPCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateInworldCredentialDtoProvider' apiKey: type: string description: >- This is the Inworld Basic (Base64) authentication token. This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: inworld variant - type: object properties: provider: type: string enum: - minimax description: 'Discriminator value: minimax' apiKey: type: string description: This is not returned in the API. groupId: type: string description: This is the Minimax Group ID. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey - groupId description: minimax variant - type: object properties: provider: $ref: '#/components/schemas/CreateWellSaidCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: wellsaid variant - type: object properties: provider: $ref: '#/components/schemas/CreateEmailCredentialDtoProvider' email: type: string description: The recipient email address for alerts name: type: string description: This is the name of credential. This is just for your reference. required: - provider - email description: email variant - type: object properties: provider: $ref: '#/components/schemas/CreateSlackWebhookCredentialDtoProvider' webhookUrl: type: string description: >- Slack incoming webhook URL. See https://api.slack.com/messaging/webhooks for setup instructions. This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - webhookUrl description: slack-webhook variant discriminator: propertyName: provider title: CreateAssistantDtoCredentialsItems CreateAssistantDtoHooksItems: oneOf: - $ref: '#/components/schemas/CallHookCallEnding' - $ref: '#/components/schemas/CallHookAssistantSpeechInterrupted' - $ref: '#/components/schemas/CallHookCustomerSpeechInterrupted' - $ref: '#/components/schemas/CallHookCustomerSpeechTimeout' - $ref: '#/components/schemas/SessionCreatedHook' title: CreateAssistantDtoHooksItems CreateAssistantDtoMetadata: type: object properties: {} description: This is for metadata you want to store on the assistant. title: CreateAssistantDtoMetadata CreateAssistantDTO: type: object properties: transcriber: $ref: '#/components/schemas/CreateAssistantDtoTranscriber' description: These are the options for the assistant's transcriber. model: $ref: '#/components/schemas/CreateAssistantDtoModel' description: These are the options for the assistant's LLM. voice: $ref: '#/components/schemas/CreateAssistantDtoVoice' description: These are the options for the assistant's voice. firstMessage: type: string description: >- This is the first message that the assistant will say. This can also be a URL to a containerized audio file (mp3, wav, etc.). If unspecified, assistant will wait for user to speak and use the model to respond once they speak. firstMessageInterruptionsEnabled: type: boolean default: false firstMessageMode: $ref: '#/components/schemas/CreateAssistantDtoFirstMessageMode' description: >- This is the mode for the first message. Default is 'assistant-speaks-first'. Use: - 'assistant-speaks-first' to have the assistant speak first. - 'assistant-waits-for-user' to have the assistant wait for the user to speak first. - 'assistant-speaks-first-with-model-generated-message' to have the assistant speak first with a message generated by the model based on the conversation state. (`assistant.model.messages` at call start, `call.messages` at squad transfer points). @default 'assistant-speaks-first' voicemailDetection: $ref: '#/components/schemas/CreateAssistantDtoVoicemailDetection' description: >- These are the settings to configure or disable voicemail detection. Alternatively, voicemail detection can be configured using the model.tools=[VoicemailTool]. By default, voicemail detection is disabled. clientMessages: $ref: '#/components/schemas/CreateAssistantDtoClientMessages' description: >- These are the messages that will be sent to your Client SDKs. Default is conversation-update,function-call,hang,model-output,speech-update,status-update,transfer-update,transcript,tool-calls,user-interrupted,voice-input,workflow.node.started,assistant.started. You can check the shape of the messages in ClientMessage schema. serverMessages: $ref: '#/components/schemas/CreateAssistantDtoServerMessages' description: >- These are the messages that will be sent to your Server URL. Default is conversation-update,end-of-call-report,function-call,hang,speech-update,status-update,tool-calls,transfer-destination-request,handoff-destination-request,user-interrupted,assistant.started. You can check the shape of the messages in ServerMessage schema. maxDurationSeconds: type: number format: double description: >- This is the maximum number of seconds that the call will last. When the call reaches this duration, it will be ended. @default 600 (10 minutes) backgroundSound: $ref: '#/components/schemas/CreateAssistantDtoBackgroundSound' description: >- This is the background sound in the call. Default for phone calls is 'office' and default for web calls is 'off'. You can also provide a custom sound by providing a URL to an audio file. modelOutputInMessagesEnabled: type: boolean description: >- This determines whether the model's output is used in conversation history rather than the transcription of assistant's speech. @default false transportConfigurations: type: array items: $ref: >- #/components/schemas/CreateAssistantDtoTransportConfigurationsItems description: >- These are the configurations to be passed to the transport providers of assistant's calls, like Twilio. You can store multiple configurations for different transport providers. For a call, only the configuration matching the call transport provider is used. observabilityPlan: $ref: '#/components/schemas/LangfuseObservabilityPlan' description: |- This is the plan for observability of assistant's calls. Currently, only Langfuse is supported. credentials: type: array items: $ref: '#/components/schemas/CreateAssistantDtoCredentialsItems' description: >- These are dynamic credentials that will be used for the assistant calls. By default, all the credentials are available for use in the call but you can supplement an additional credentials using this. Dynamic credentials override existing credentials. hooks: type: array items: $ref: '#/components/schemas/CreateAssistantDtoHooksItems' description: This is a set of actions that will be performed on certain events. name: type: string description: >- This is the name of the assistant. This is required when you want to transfer between assistants in a call. voicemailMessage: type: string description: >- This is the message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up. endCallMessage: type: string description: |- This is the message that the assistant will say if it ends the call. If unspecified, it will hang up without saying anything. endCallPhrases: type: array items: type: string description: >- This list contains phrases that, if spoken by the assistant, will trigger the call to be hung up. Case insensitive. compliancePlan: $ref: '#/components/schemas/CompliancePlan' metadata: $ref: '#/components/schemas/CreateAssistantDtoMetadata' description: This is for metadata you want to store on the assistant. backgroundSpeechDenoisingPlan: $ref: '#/components/schemas/BackgroundSpeechDenoisingPlan' description: >- This enables filtering of noise and background speech while the user is talking. Features: - Smart denoising using Krisp - Fourier denoising Smart denoising can be combined with or used independently of Fourier denoising. Order of precedence: - Smart denoising - Fourier denoising analysisPlan: $ref: '#/components/schemas/AnalysisPlan' description: >- This is the plan for analysis of assistant's calls. Stored in `call.analysis`. artifactPlan: $ref: '#/components/schemas/ArtifactPlan' description: >- This is the plan for artifacts generated during assistant's calls. Stored in `call.artifact`. startSpeakingPlan: $ref: '#/components/schemas/StartSpeakingPlan' description: >- This is the plan for when the assistant should start talking. You should configure this if you're running into these issues: - The assistant is too slow to start talking after the customer is done speaking. - The assistant is too fast to start talking after the customer is done speaking. - The assistant is so fast that it's actually interrupting the customer. stopSpeakingPlan: $ref: '#/components/schemas/StopSpeakingPlan' description: >- This is the plan for when assistant should stop talking on customer interruption. You should configure this if you're running into these issues: - The assistant is too slow to recognize customer's interruption. - The assistant is too fast to recognize customer's interruption. - The assistant is getting interrupted by phrases that are just acknowledgments. - The assistant is getting interrupted by background noises. - The assistant is not properly stopping -- it starts talking right after getting interrupted. monitorPlan: $ref: '#/components/schemas/MonitorPlan' description: >- This is the plan for real-time monitoring of the assistant's calls. Usage: - To enable live listening of the assistant's calls, set `monitorPlan.listenEnabled` to `true`. - To enable live control of the assistant's calls, set `monitorPlan.controlEnabled` to `true`. - To attach monitors to the assistant, set `monitorPlan.monitorIds` to the set of monitor ids. credentialIds: type: array items: type: string description: >- These are the credentials that will be used for the assistant calls. By default, all the credentials are available for use in the call but you can provide a subset using this. server: $ref: '#/components/schemas/Server' description: >- This is where Vapi will send webhooks. You can find all webhooks available along with their shape in ServerMessage schema. The order of precedence is: 1. assistant.server.url 2. phoneNumber.serverUrl 3. org.serverUrl keypadInputPlan: $ref: '#/components/schemas/KeypadInputPlan' title: CreateAssistantDTO ConversationNodeType: type: string enum: - conversation description: >- This is the Conversation node. This can be used to start a conversation with the customer. The flow is: - Workflow starts the conversation node - Model is active with the `prompt` and global context. - Model will call a tool to exit this node. - Workflow will extract variables from the conversation. - Workflow continues. title: ConversationNodeType ConversationNodeModel: oneOf: - $ref: '#/components/schemas/WorkflowOpenAIModel' - $ref: '#/components/schemas/WorkflowAnthropicModel' - $ref: '#/components/schemas/WorkflowAnthropicBedrockModel' - $ref: '#/components/schemas/WorkflowGoogleModel' - $ref: '#/components/schemas/WorkflowCustomModel' description: |- This is the model for the node. This overrides `workflow.model`. title: ConversationNodeModel ConversationNodeTranscriber: oneOf: - $ref: '#/components/schemas/AssemblyAITranscriber' - $ref: '#/components/schemas/AzureSpeechTranscriber' - $ref: '#/components/schemas/CustomTranscriber' - $ref: '#/components/schemas/DeepgramTranscriber' - $ref: '#/components/schemas/ElevenLabsTranscriber' - $ref: '#/components/schemas/GladiaTranscriber' - $ref: '#/components/schemas/GoogleTranscriber' - $ref: '#/components/schemas/SpeechmaticsTranscriber' - $ref: '#/components/schemas/TalkscriberTranscriber' - $ref: '#/components/schemas/OpenAITranscriber' - $ref: '#/components/schemas/CartesiaTranscriber' - $ref: '#/components/schemas/SonioxTranscriber' description: |- This is the transcriber for the node. This overrides `workflow.transcriber`. title: ConversationNodeTranscriber ConversationNodeVoice: oneOf: - $ref: '#/components/schemas/AzureVoice' - $ref: '#/components/schemas/CartesiaVoice' - $ref: '#/components/schemas/CustomVoice' - $ref: '#/components/schemas/DeepgramVoice' - $ref: '#/components/schemas/ElevenLabsVoice' - $ref: '#/components/schemas/HumeVoice' - $ref: '#/components/schemas/LMNTVoice' - $ref: '#/components/schemas/NeuphonicVoice' - $ref: '#/components/schemas/OpenAIVoice' - $ref: '#/components/schemas/PlayHTVoice' - $ref: '#/components/schemas/WellSaidVoice' - $ref: '#/components/schemas/RimeAIVoice' - $ref: '#/components/schemas/SmallestAIVoice' - $ref: '#/components/schemas/TavusVoice' - $ref: '#/components/schemas/VapiVoice' - $ref: '#/components/schemas/SesameVoice' - $ref: '#/components/schemas/InworldVoice' - $ref: '#/components/schemas/MinimaxVoice' description: |- This is the voice for the node. This overrides `workflow.voice`. title: ConversationNodeVoice ConversationNodeToolsItems: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' title: ConversationNodeToolsItems GlobalNodePlan: type: object properties: enabled: type: boolean default: false description: |- This is the flag to determine if this node is a global node @default false enterCondition: type: string default: '' description: >- This is the condition that will be checked to determine if the global node should be executed. @default '' title: GlobalNodePlan ConversationNodeMetadata: type: object properties: {} description: This is for metadata you want to store on the task. title: ConversationNodeMetadata ConversationNode: type: object properties: type: $ref: '#/components/schemas/ConversationNodeType' description: >- This is the Conversation node. This can be used to start a conversation with the customer. The flow is: - Workflow starts the conversation node - Model is active with the `prompt` and global context. - Model will call a tool to exit this node. - Workflow will extract variables from the conversation. - Workflow continues. model: $ref: '#/components/schemas/ConversationNodeModel' description: |- This is the model for the node. This overrides `workflow.model`. transcriber: $ref: '#/components/schemas/ConversationNodeTranscriber' description: |- This is the transcriber for the node. This overrides `workflow.transcriber`. voice: $ref: '#/components/schemas/ConversationNodeVoice' description: |- This is the voice for the node. This overrides `workflow.voice`. tools: type: array items: $ref: '#/components/schemas/ConversationNodeToolsItems' description: >- These are the tools that the conversation node can use during the call. To use existing tools, use `toolIds`. Both `tools` and `toolIds` can be used together. toolIds: type: array items: type: string description: >- These are the tools that the conversation node can use during the call. To use transient tools, use `tools`. Both `tools` and `toolIds` can be used together. prompt: type: string globalNodePlan: $ref: '#/components/schemas/GlobalNodePlan' description: This is the plan for the global node. variableExtractionPlan: $ref: '#/components/schemas/VariableExtractionPlan' description: >- This is the plan that controls the variable extraction from the user's responses. Usage: Use `schema` to specify what you want to extract from the user's responses. ```json { "schema": { "type": "object", "properties": { "user": { "type": "object", "properties": { "name": { "type": "string" }, "age": { "type": "number" } } } } } } ``` This will be extracted as `{{ user.name }}` and `{{ user.age }}` respectively. (Optional) Use `aliases` to create new variables. ```json { "aliases": [ { "key": "userAge", "value": "{{user.age}}" }, { "key": "userName", "value": "{{user.name}}" } ] } ``` This will be extracted as `{{ userAge }}` and `{{ userName }}` respectively. Note: The `schema` field is required for Conversation nodes if you want to extract variables from the user's responses. `aliases` is just a convenience. name: type: string isStart: type: boolean description: This is whether or not the node is the start of the workflow. metadata: $ref: '#/components/schemas/ConversationNodeMetadata' description: This is for metadata you want to store on the task. required: - type - name title: ConversationNode ToolNodeType: type: string enum: - tool description: >- This is the Tool node. This can be used to call a tool in your workflow. The flow is: - Workflow starts the tool node - Model is called to extract parameters needed by the tool from the conversation history - Tool is called with the parameters - Server returns a response - Workflow continues with the response title: ToolNodeType ToolNodeTool: oneOf: - $ref: '#/components/schemas/CreateApiRequestToolDTO' - $ref: '#/components/schemas/CreateBashToolDTO' - $ref: '#/components/schemas/CreateCodeToolDTO' - $ref: '#/components/schemas/CreateComputerToolDTO' - $ref: '#/components/schemas/CreateDtmfToolDTO' - $ref: '#/components/schemas/CreateEndCallToolDTO' - $ref: '#/components/schemas/CreateFunctionToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelCalendarEventCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactCreateToolDTO' - $ref: '#/components/schemas/CreateGoHighLevelContactGetToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCheckAvailabilityToolDTO' - $ref: '#/components/schemas/CreateGoogleCalendarCreateEventToolDTO' - $ref: '#/components/schemas/CreateGoogleSheetsRowAppendToolDTO' - $ref: '#/components/schemas/CreateHandoffToolDTO' - $ref: '#/components/schemas/CreateMcpToolDTO' - $ref: '#/components/schemas/CreateQueryToolDTO' - $ref: '#/components/schemas/CreateSlackSendMessageToolDTO' - $ref: '#/components/schemas/CreateSmsToolDTO' - $ref: '#/components/schemas/CreateTextEditorToolDTO' - $ref: '#/components/schemas/CreateTransferCallToolDTO' - $ref: '#/components/schemas/CreateSipRequestToolDTO' - $ref: '#/components/schemas/CreateVoicemailToolDTO' description: >- This is the tool to call. To use an existing tool, send `toolId` instead. title: ToolNodeTool ToolNodeMetadata: type: object properties: {} description: This is for metadata you want to store on the task. title: ToolNodeMetadata ToolNode: type: object properties: type: $ref: '#/components/schemas/ToolNodeType' description: >- This is the Tool node. This can be used to call a tool in your workflow. The flow is: - Workflow starts the tool node - Model is called to extract parameters needed by the tool from the conversation history - Tool is called with the parameters - Server returns a response - Workflow continues with the response tool: $ref: '#/components/schemas/ToolNodeTool' description: >- This is the tool to call. To use an existing tool, send `toolId` instead. toolId: type: string description: >- This is the tool to call. To use a transient tool, send `tool` instead. name: type: string isStart: type: boolean description: This is whether or not the node is the start of the workflow. metadata: $ref: '#/components/schemas/ToolNodeMetadata' description: This is for metadata you want to store on the task. required: - type - name title: ToolNode CreateWorkflowDtoNodesItems: oneOf: - $ref: '#/components/schemas/ConversationNode' - $ref: '#/components/schemas/ToolNode' title: CreateWorkflowDtoNodesItems CreateWorkflowDtoModel: oneOf: - $ref: '#/components/schemas/WorkflowOpenAIModel' - $ref: '#/components/schemas/WorkflowAnthropicModel' - $ref: '#/components/schemas/WorkflowAnthropicBedrockModel' - $ref: '#/components/schemas/WorkflowGoogleModel' - $ref: '#/components/schemas/WorkflowCustomModel' description: |- This is the model for the workflow. This can be overridden at node level using `nodes[n].model`. title: CreateWorkflowDtoModel CreateWorkflowDtoTranscriber: oneOf: - $ref: '#/components/schemas/AssemblyAITranscriber' - $ref: '#/components/schemas/AzureSpeechTranscriber' - $ref: '#/components/schemas/CustomTranscriber' - $ref: '#/components/schemas/DeepgramTranscriber' - $ref: '#/components/schemas/ElevenLabsTranscriber' - $ref: '#/components/schemas/GladiaTranscriber' - $ref: '#/components/schemas/GoogleTranscriber' - $ref: '#/components/schemas/SpeechmaticsTranscriber' - $ref: '#/components/schemas/TalkscriberTranscriber' - $ref: '#/components/schemas/OpenAITranscriber' - $ref: '#/components/schemas/CartesiaTranscriber' - $ref: '#/components/schemas/SonioxTranscriber' description: |- This is the transcriber for the workflow. This can be overridden at node level using `nodes[n].transcriber`. title: CreateWorkflowDtoTranscriber CreateWorkflowDtoVoice: oneOf: - $ref: '#/components/schemas/AzureVoice' - $ref: '#/components/schemas/CartesiaVoice' - $ref: '#/components/schemas/CustomVoice' - $ref: '#/components/schemas/DeepgramVoice' - $ref: '#/components/schemas/ElevenLabsVoice' - $ref: '#/components/schemas/HumeVoice' - $ref: '#/components/schemas/LMNTVoice' - $ref: '#/components/schemas/NeuphonicVoice' - $ref: '#/components/schemas/OpenAIVoice' - $ref: '#/components/schemas/PlayHTVoice' - $ref: '#/components/schemas/WellSaidVoice' - $ref: '#/components/schemas/RimeAIVoice' - $ref: '#/components/schemas/SmallestAIVoice' - $ref: '#/components/schemas/TavusVoice' - $ref: '#/components/schemas/VapiVoice' - $ref: '#/components/schemas/SesameVoice' - $ref: '#/components/schemas/InworldVoice' - $ref: '#/components/schemas/MinimaxVoice' description: |- This is the voice for the workflow. This can be overridden at node level using `nodes[n].voice`. title: CreateWorkflowDtoVoice CreateWorkflowDtoBackgroundSound0: type: string enum: - 'off' - office title: CreateWorkflowDtoBackgroundSound0 CreateWorkflowDtoBackgroundSound: oneOf: - $ref: '#/components/schemas/CreateWorkflowDtoBackgroundSound0' - type: string format: uri description: >- This is the background sound in the call. Default for phone calls is 'office' and default for web calls is 'off'. You can also provide a custom sound by providing a URL to an audio file. title: CreateWorkflowDtoBackgroundSound CallHookModelResponseTimeoutOn: type: string enum: - model.response.timeout description: This is the event that triggers this hook title: CallHookModelResponseTimeoutOn CallHookModelResponseTimeoutDoItems: oneOf: - $ref: '#/components/schemas/SayHookAction' - $ref: '#/components/schemas/ToolCallHookAction' - $ref: '#/components/schemas/MessageAddHookAction' title: CallHookModelResponseTimeoutDoItems CallHookModelResponseTimeout: type: object properties: 'on': $ref: '#/components/schemas/CallHookModelResponseTimeoutOn' description: This is the event that triggers this hook do: type: array items: $ref: '#/components/schemas/CallHookModelResponseTimeoutDoItems' description: This is the set of actions to perform when the hook triggers required: - 'on' - do title: CallHookModelResponseTimeout CreateWorkflowDtoHooksItems: oneOf: - $ref: '#/components/schemas/CallHookCallEnding' - $ref: '#/components/schemas/CallHookAssistantSpeechInterrupted' - $ref: '#/components/schemas/CallHookCustomerSpeechInterrupted' - $ref: '#/components/schemas/CallHookCustomerSpeechTimeout' - $ref: '#/components/schemas/CallHookModelResponseTimeout' title: CreateWorkflowDtoHooksItems CreateWorkflowDtoCredentialsItems: oneOf: - type: object properties: provider: type: string enum: - 11labs description: 'Discriminator value: 11labs' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateElevenLabsCredentialDTO variant - type: object properties: provider: type: string enum: - anthropic description: 'Discriminator value: anthropic' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateAnthropicCredentialDTO variant - type: object properties: provider: type: string enum: - anthropic-bedrock description: 'Discriminator value: anthropic-bedrock' region: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockRegion description: AWS region where Bedrock is configured. authenticationPlan: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAnthropicBedrockAuthenticationPlan description: >- Authentication method - either direct IAM credentials or cross-account role assumption. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - region - authenticationPlan description: anthropic-bedrock variant - type: object properties: provider: type: string enum: - anyscale description: 'Discriminator value: anyscale' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateAnyscaleCredentialDTO variant - type: object properties: provider: type: string enum: - assembly-ai description: 'Discriminator value: assembly-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateAssemblyAICredentialDTO variant - type: object properties: provider: type: string enum: - azure-openai description: 'Discriminator value: azure-openai' region: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiRegion models: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureOpenaiModels openAIKey: type: string description: This is not returned in the API. ocpApimSubscriptionKey: type: string description: This is not returned in the API. openAIEndpoint: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - region - models - openAIKey - openAIEndpoint description: CreateAzureOpenAICredentialDTO variant - type: object properties: provider: type: string enum: - azure description: 'Discriminator value: azure' service: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureService description: This is the service being used in Azure. region: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingAzureRegion description: This is the region of the Azure resource. apiKey: type: string description: This is not returned in the API. fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/AzureBlobStorageBucketPlan' description: >- This is the bucket plan that can be provided to store call artifacts in Azure Blob Storage. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - service description: CreateAzureCredentialDTO variant - type: object properties: provider: type: string enum: - byo-sip-trunk description: 'Discriminator value: byo-sip-trunk' gateways: type: array items: $ref: '#/components/schemas/SipTrunkGateway' description: This is the list of SIP trunk's gateways. outboundAuthenticationPlan: $ref: '#/components/schemas/SipTrunkOutboundAuthenticationPlan' description: >- This can be used to configure the outbound authentication if required by the SIP trunk. outboundLeadingPlusEnabled: type: boolean description: >- This ensures the outbound origination attempts have a leading plus. Defaults to false to match conventional telecom behavior. Usage: - Vonage/Twilio requires leading plus for all outbound calls. Set this to true. @default false techPrefix: type: string description: >- This can be used to configure the tech prefix on outbound calls. This is an advanced property. sipDiversionHeader: type: string description: >- This can be used to enable the SIP diversion header for authenticating the calling number if the SIP trunk supports it. This is an advanced property. sbcConfiguration: $ref: '#/components/schemas/SbcConfiguration' description: >- This is an advanced configuration for enterprise deployments. This uses the onprem SBC to trunk into the SIP trunk's `gateways`, rather than the managed SBC provided by Vapi. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - gateways description: CreateByoSipTrunkCredentialDTO variant - type: object properties: provider: type: string enum: - cartesia description: 'Discriminator value: cartesia' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateCartesiaCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateCerebrasCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateCerebrasCredentialDTO variant - type: object properties: provider: type: string enum: - cloudflare description: 'Discriminator value: cloudflare' accountId: type: string description: Cloudflare Account Id. apiKey: type: string description: Cloudflare API Key / Token. accountEmail: type: string description: Cloudflare Account Email. fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/CloudflareR2BucketPlan' description: >- This is the bucket plan that can be provided to store call artifacts in R2 name: type: string description: This is the name of credential. This is just for your reference. required: - provider description: CreateCloudflareCredentialDTO variant - type: object properties: provider: type: string enum: - custom-llm description: 'Discriminator value: custom-llm' apiKey: type: string description: This is not returned in the API. authenticationPlan: $ref: '#/components/schemas/OAuth2AuthenticationPlan' description: >- This is the authentication plan. Currently supports OAuth2 RFC 6749. To use Bearer authentication, use apiKey name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateCustomLLMCredentialDTO variant - type: object properties: provider: type: string enum: - deepgram description: 'Discriminator value: deepgram' apiKey: type: string description: This is not returned in the API. apiUrl: type: string description: >- This can be used to point to an onprem Deepgram instance. Defaults to api.deepgram.com. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateDeepgramCredentialDTO variant - type: object properties: provider: type: string enum: - deepinfra description: 'Discriminator value: deepinfra' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateDeepInfraCredentialDTO variant - type: object properties: provider: type: string enum: - deep-seek description: 'Discriminator value: deep-seek' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateDeepSeekCredentialDTO variant - type: object properties: provider: type: string enum: - gcp description: 'Discriminator value: gcp' fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. gcpKey: $ref: '#/components/schemas/GcpKey' description: >- This is the GCP key. This is the JSON that can be generated in the Google Cloud Console at https://console.cloud.google.com/iam-admin/serviceaccounts/details//keys. The schema is identical to the JSON that GCP outputs. region: type: string description: This is the region of the GCP resource. bucketPlan: $ref: '#/components/schemas/BucketPlan' name: type: string description: This is the name of credential. This is just for your reference. required: - provider - gcpKey description: CreateGcpCredentialDTO variant - type: object properties: provider: type: string enum: - gladia description: 'Discriminator value: gladia' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGladiaCredentialDTO variant - type: object properties: provider: type: string enum: - gohighlevel description: 'Discriminator value: gohighlevel' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGoHighLevelCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateGoogleCredentialDtoProvider' description: >- This is the key for Gemini in Google AI Studio. Get it from here: https://aistudio.google.com/app/apikey apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGoogleCredentialDTO variant - type: object properties: provider: type: string enum: - groq description: 'Discriminator value: groq' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateGroqCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateInflectionAiCredentialDtoProvider' description: >- This is the api key for Pi in InflectionAI's console. Get it from here: https://developers.inflection.ai/keys, billing will need to be setup apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateInflectionAICredentialDTO variant - type: object properties: provider: type: string enum: - langfuse description: 'Discriminator value: langfuse' publicKey: type: string description: 'The public key for Langfuse project. Eg: pk-lf-...' apiKey: type: string description: >- The secret key for Langfuse project. Eg: sk-lf-... .This is not returned in the API. apiUrl: type: string description: >- The host URL for Langfuse project. Eg: https://cloud.langfuse.com name: type: string description: This is the name of credential. This is just for your reference. required: - provider - publicKey - apiKey - apiUrl description: CreateLangfuseCredentialDTO variant - type: object properties: provider: type: string enum: - lmnt description: 'Discriminator value: lmnt' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateLmntCredentialDTO variant - type: object properties: provider: type: string enum: - make description: 'Discriminator value: make' teamId: type: string description: Team ID region: type: string description: 'Region of your application. For example: eu1, eu2, us1, us2' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - teamId - region - apiKey description: CreateMakeCredentialDTO variant - type: object properties: provider: type: string enum: - openai description: 'Discriminator value: openai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateOpenAICredentialDTO variant - type: object properties: provider: type: string enum: - openrouter description: 'Discriminator value: openrouter' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateOpenRouterCredentialDTO variant - type: object properties: provider: type: string enum: - perplexity-ai description: 'Discriminator value: perplexity-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreatePerplexityAICredentialDTO variant - type: object properties: provider: type: string enum: - playht description: 'Discriminator value: playht' apiKey: type: string description: This is not returned in the API. userId: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey - userId description: CreatePlayHTCredentialDTO variant - type: object properties: provider: type: string enum: - rime-ai description: 'Discriminator value: rime-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateRimeAICredentialDTO variant - type: object properties: provider: type: string enum: - runpod description: 'Discriminator value: runpod' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateRunpodCredentialDTO variant - type: object properties: provider: type: string enum: - s3 description: 'Discriminator value: s3' awsAccessKeyId: type: string description: AWS access key ID. awsSecretAccessKey: type: string description: AWS access key secret. This is not returned in the API. region: type: string description: AWS region in which the S3 bucket is located. s3BucketName: type: string description: AWS S3 bucket name. s3PathPrefix: type: string description: The path prefix for the uploaded recording. Ex. "recordings/" fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - awsAccessKeyId - awsSecretAccessKey - region - s3BucketName - s3PathPrefix description: CreateS3CredentialDTO variant - type: object properties: provider: type: string enum: - supabase description: 'Discriminator value: supabase' fallbackIndex: type: number format: double description: >- This is the order in which this storage provider is tried during upload retries. Lower numbers are tried first in increasing order. bucketPlan: $ref: '#/components/schemas/SupabaseBucketPlan' name: type: string description: This is the name of credential. This is just for your reference. required: - provider description: CreateSupabaseCredentialDTO variant - type: object properties: provider: type: string enum: - smallest-ai description: 'Discriminator value: smallest-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateSmallestAICredentialDTO variant - type: object properties: provider: type: string enum: - tavus description: 'Discriminator value: tavus' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateTavusCredentialDTO variant - type: object properties: provider: type: string enum: - together-ai description: 'Discriminator value: together-ai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateTogetherAICredentialDTO variant - type: object properties: provider: type: string enum: - twilio description: 'Discriminator value: twilio' authToken: type: string description: This is not returned in the API. apiKey: type: string description: This is not returned in the API. apiSecret: type: string description: This is not returned in the API. accountSid: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - accountSid description: CreateTwilioCredentialDTO variant - type: object properties: provider: type: string enum: - vonage description: 'Discriminator value: vonage' apiSecret: type: string description: This is not returned in the API. apiKey: type: string name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiSecret - apiKey description: CreateVonageCredentialDTO variant - type: object properties: provider: type: string enum: - webhook description: 'Discriminator value: webhook' authenticationPlan: $ref: >- #/components/schemas/UpdateWorkflowDtoCredentialsItemsDiscriminatorMappingWebhookAuthenticationPlan description: >- This is the authentication plan. Supports OAuth2 RFC 6749, HMAC signing, and Bearer authentication. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authenticationPlan description: CreateWebhookCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateCustomCredentialDtoProvider' authenticationPlan: $ref: '#/components/schemas/CreateCustomCredentialDtoAuthenticationPlan' description: >- This is the authentication plan. Supports OAuth2 RFC 6749, HMAC signing, and Bearer authentication. encryptionPlan: $ref: '#/components/schemas/PublicKeyEncryptionPlan' description: >- This is the encryption plan for encrypting sensitive data. Currently supports public-key encryption. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authenticationPlan description: custom-credential variant - type: object properties: provider: type: string enum: - xai description: 'Discriminator value: xai' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateXAiCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateNeuphonicCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateNeuphonicCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateHumeCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateHumeCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateMistralCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateMistralCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateSpeechmaticsCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateSpeechmaticsCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateSonioxCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: soniox variant - type: object properties: provider: $ref: '#/components/schemas/CreateTrieveCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: CreateTrieveCredentialDTO variant - type: object properties: provider: type: string enum: - google.calendar.oauth2-client description: 'Discriminator value: google.calendar.oauth2-client' name: type: string description: This is the name of credential. This is just for your reference. required: - provider description: CreateGoogleCalendarOAuth2ClientCredentialDTO variant - type: object properties: provider: type: string enum: - google.calendar.oauth2-authorization description: 'Discriminator value: google.calendar.oauth2-authorization' authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authorizationId description: CreateGoogleCalendarOAuth2AuthorizationCredentialDTO variant - type: object properties: provider: type: string enum: - google.sheets.oauth2-authorization description: 'Discriminator value: google.sheets.oauth2-authorization' authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authorizationId description: CreateGoogleSheetsOAuth2AuthorizationCredentialDTO variant - type: object properties: provider: type: string enum: - slack.oauth2-authorization description: 'Discriminator value: slack.oauth2-authorization' authorizationId: type: string description: The authorization ID for the OAuth2 authorization name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authorizationId description: CreateSlackOAuth2AuthorizationCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateGoHighLevelMcpCredentialDtoProvider' authenticationSession: $ref: '#/components/schemas/Oauth2AuthenticationSession' description: This is the authentication session for the credential. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - authenticationSession description: CreateGoHighLevelMCPCredentialDTO variant - type: object properties: provider: $ref: '#/components/schemas/CreateInworldCredentialDtoProvider' apiKey: type: string description: >- This is the Inworld Basic (Base64) authentication token. This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: inworld variant - type: object properties: provider: type: string enum: - minimax description: 'Discriminator value: minimax' apiKey: type: string description: This is not returned in the API. groupId: type: string description: This is the Minimax Group ID. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey - groupId description: minimax variant - type: object properties: provider: $ref: '#/components/schemas/CreateWellSaidCredentialDtoProvider' apiKey: type: string description: This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - apiKey description: wellsaid variant - type: object properties: provider: $ref: '#/components/schemas/CreateEmailCredentialDtoProvider' email: type: string description: The recipient email address for alerts name: type: string description: This is the name of credential. This is just for your reference. required: - provider - email description: email variant - type: object properties: provider: $ref: '#/components/schemas/CreateSlackWebhookCredentialDtoProvider' webhookUrl: type: string description: >- Slack incoming webhook URL. See https://api.slack.com/messaging/webhooks for setup instructions. This is not returned in the API. name: type: string description: This is the name of credential. This is just for your reference. required: - provider - webhookUrl description: slack-webhook variant discriminator: propertyName: provider title: CreateWorkflowDtoCredentialsItems CreateWorkflowDtoVoicemailDetection0: type: string enum: - 'off' title: CreateWorkflowDtoVoicemailDetection0 CreateWorkflowDtoVoicemailDetection: oneOf: - $ref: '#/components/schemas/CreateWorkflowDtoVoicemailDetection0' - $ref: '#/components/schemas/GoogleVoicemailDetectionPlan' - $ref: '#/components/schemas/OpenAIVoicemailDetectionPlan' - $ref: '#/components/schemas/TwilioVoicemailDetectionPlan' - $ref: '#/components/schemas/VapiVoicemailDetectionPlan' description: This is the voicemail detection plan for the workflow. title: CreateWorkflowDtoVoicemailDetection AiEdgeConditionType: type: string enum: - ai title: AiEdgeConditionType AIEdgeCondition: type: object properties: type: $ref: '#/components/schemas/AiEdgeConditionType' prompt: type: string description: >- This is the prompt for the AI edge condition. It should evaluate to a boolean. required: - type - prompt title: AIEdgeCondition EdgeCondition: oneOf: - $ref: '#/components/schemas/AIEdgeCondition' title: EdgeCondition EdgeMetadata: type: object properties: {} description: This is for metadata you want to store on the edge. title: EdgeMetadata Edge: type: object properties: condition: $ref: '#/components/schemas/EdgeCondition' from: type: string to: type: string metadata: $ref: '#/components/schemas/EdgeMetadata' description: This is for metadata you want to store on the edge. required: - from - to title: Edge CreateWorkflowDTO: type: object properties: nodes: type: array items: $ref: '#/components/schemas/CreateWorkflowDtoNodesItems' model: $ref: '#/components/schemas/CreateWorkflowDtoModel' description: |- This is the model for the workflow. This can be overridden at node level using `nodes[n].model`. transcriber: $ref: '#/components/schemas/CreateWorkflowDtoTranscriber' description: |- This is the transcriber for the workflow. This can be overridden at node level using `nodes[n].transcriber`. voice: $ref: '#/components/schemas/CreateWorkflowDtoVoice' description: |- This is the voice for the workflow. This can be overridden at node level using `nodes[n].voice`. observabilityPlan: $ref: '#/components/schemas/LangfuseObservabilityPlan' description: |- This is the plan for observability of workflow's calls. Currently, only Langfuse is supported. backgroundSound: $ref: '#/components/schemas/CreateWorkflowDtoBackgroundSound' description: >- This is the background sound in the call. Default for phone calls is 'office' and default for web calls is 'off'. You can also provide a custom sound by providing a URL to an audio file. hooks: type: array items: $ref: '#/components/schemas/CreateWorkflowDtoHooksItems' description: This is a set of actions that will be performed on certain events. credentials: type: array items: $ref: '#/components/schemas/CreateWorkflowDtoCredentialsItems' description: >- These are dynamic credentials that will be used for the workflow calls. By default, all the credentials are available for use in the call but you can supplement an additional credentials using this. Dynamic credentials override existing credentials. voicemailDetection: $ref: '#/components/schemas/CreateWorkflowDtoVoicemailDetection' description: This is the voicemail detection plan for the workflow. maxDurationSeconds: type: number format: double description: >- This is the maximum duration of the call in seconds. After this duration, the call will automatically end. Default is 1800 (30 minutes), max is 43200 (12 hours), and min is 10 seconds. name: type: string edges: type: array items: $ref: '#/components/schemas/Edge' globalPrompt: type: string server: $ref: '#/components/schemas/Server' description: >- This is where Vapi will send webhooks. You can find all webhooks available along with their shape in ServerMessage schema. The order of precedence is: 1. tool.server 2. workflow.server / assistant.server 3. phoneNumber.server 4. org.server compliancePlan: $ref: '#/components/schemas/CompliancePlan' description: >- This is the compliance plan for the workflow. It allows you to configure HIPAA and other compliance settings. analysisPlan: $ref: '#/components/schemas/AnalysisPlan' description: >- This is the plan for analysis of workflow's calls. Stored in `call.analysis`. artifactPlan: $ref: '#/components/schemas/ArtifactPlan' description: >- This is the plan for artifacts generated during workflow's calls. Stored in `call.artifact`. startSpeakingPlan: $ref: '#/components/schemas/StartSpeakingPlan' description: >- This is the plan for when the workflow nodes should start talking. You should configure this if you're running into these issues: - The assistant is too slow to start talking after the customer is done speaking. - The assistant is too fast to start talking after the customer is done speaking. - The assistant is so fast that it's actually interrupting the customer. stopSpeakingPlan: $ref: '#/components/schemas/StopSpeakingPlan' description: >- This is the plan for when workflow nodes should stop talking on customer interruption. You should configure this if you're running into these issues: - The assistant is too slow to recognize customer's interruption. - The assistant is too fast to recognize customer's interruption. - The assistant is getting interrupted by phrases that are just acknowledgments. - The assistant is getting interrupted by background noises. - The assistant is not properly stopping -- it starts talking right after getting interrupted. monitorPlan: $ref: '#/components/schemas/MonitorPlan' description: >- This is the plan for real-time monitoring of the workflow's calls. Usage: - To enable live listening of the workflow's calls, set `monitorPlan.listenEnabled` to `true`. - To enable live control of the workflow's calls, set `monitorPlan.controlEnabled` to `true`. backgroundSpeechDenoisingPlan: $ref: '#/components/schemas/BackgroundSpeechDenoisingPlan' description: >- This enables filtering of noise and background speech while the user is talking. Features: - Smart denoising using Krisp - Fourier denoising Both can be used together. Order of precedence: - Smart denoising - Fourier denoising credentialIds: type: array items: type: string description: >- These are the credentials that will be used for the workflow calls. By default, all the credentials are available for use in the call but you can provide a subset using this. keypadInputPlan: $ref: '#/components/schemas/KeypadInputPlan' description: This is the plan for keypad input handling during workflow calls. voicemailMessage: type: string description: >- This is the message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up. required: - nodes - name - edges title: CreateWorkflowDTO WorkflowOverridesVariableValues: type: object properties: {} description: >- These are values that will be used to replace the template variables in the workflow messages and other text-based fields. This uses LiquidJS syntax. https://liquidjs.com/tutorials/intro-to-liquid.html So for example, `{{ name }}` will be replaced with the value of `name` in `variableValues`. `{{"now" | date: "%b %d, %Y, %I:%M %p", "America/New_York"}}` will be replaced with the current date and time in New York. Some VAPI reserved defaults: - *customer* - the customer object title: WorkflowOverridesVariableValues WorkflowOverrides: type: object properties: variableValues: $ref: '#/components/schemas/WorkflowOverridesVariableValues' description: >- These are values that will be used to replace the template variables in the workflow messages and other text-based fields. This uses LiquidJS syntax. https://liquidjs.com/tutorials/intro-to-liquid.html So for example, `{{ name }}` will be replaced with the value of `name` in `variableValues`. `{{"now" | date: "%b %d, %Y, %I:%M %p", "America/New_York"}}` will be replaced with the current date and time in New York. Some VAPI reserved defaults: - *customer* - the customer object title: WorkflowOverrides ImportTwilioPhoneNumberDtoFallbackDestination: oneOf: - $ref: '#/components/schemas/TransferDestinationNumber' - $ref: '#/components/schemas/TransferDestinationSip' description: >- This is the fallback destination an inbound call will be transferred to if: 1. `assistantId` is not set 2. `squadId` is not set 3. and, `assistant-request` message to the `serverUrl` fails If this is not set and above conditions are met, the inbound call is hung up with an error message. title: ImportTwilioPhoneNumberDtoFallbackDestination PhoneNumberHookCallRingingOn: type: string enum: - call.ringing description: This is the event to trigger the hook on title: PhoneNumberHookCallRingingOn PhoneNumberCallRingingHookFilterType: type: string enum: - startsWith description: >- This is the type of filter - matches when the specified field starts with any of the given prefixes title: PhoneNumberCallRingingHookFilterType PhoneNumberCallRingingHookFilterKey: type: string enum: - number description: >- The field to check. Currently only "number" (the caller's phone number) is supported. title: PhoneNumberCallRingingHookFilterKey PhoneNumberCallRingingHookFilter: type: object properties: type: $ref: '#/components/schemas/PhoneNumberCallRingingHookFilterType' description: >- This is the type of filter - matches when the specified field starts with any of the given prefixes key: $ref: '#/components/schemas/PhoneNumberCallRingingHookFilterKey' description: >- The field to check. Currently only "number" (the caller's phone number) is supported. startsWith: type: array items: type: string description: >- Array of prefixes to match. Do not include the + prefix. Inbound calls from numbers starting with any of these prefixes will trigger the hook actions. required: - type - key - startsWith title: PhoneNumberCallRingingHookFilter TransferPhoneNumberHookActionType: type: string enum: - transfer description: This is the type of action - must be "transfer" title: TransferPhoneNumberHookActionType TransferPhoneNumberHookActionDestination: oneOf: - $ref: '#/components/schemas/TransferDestinationNumber' - $ref: '#/components/schemas/TransferDestinationSip' description: >- This is the destination details for the transfer - can be a phone number or SIP URI title: TransferPhoneNumberHookActionDestination TransferPhoneNumberHookAction: type: object properties: type: $ref: '#/components/schemas/TransferPhoneNumberHookActionType' description: This is the type of action - must be "transfer" destination: $ref: '#/components/schemas/TransferPhoneNumberHookActionDestination' description: >- This is the destination details for the transfer - can be a phone number or SIP URI required: - type title: TransferPhoneNumberHookAction SayPhoneNumberHookActionType: type: string enum: - say description: This is the type of action - must be "say" title: SayPhoneNumberHookActionType SayPhoneNumberHookAction: type: object properties: type: $ref: '#/components/schemas/SayPhoneNumberHookActionType' description: This is the type of action - must be "say" exact: type: string description: This is the message to say required: - type - exact title: SayPhoneNumberHookAction PhoneNumberHookCallRingingDoItems: oneOf: - $ref: '#/components/schemas/TransferPhoneNumberHookAction' - $ref: '#/components/schemas/SayPhoneNumberHookAction' title: PhoneNumberHookCallRingingDoItems PhoneNumberHookCallRinging: type: object properties: 'on': $ref: '#/components/schemas/PhoneNumberHookCallRingingOn' description: This is the event to trigger the hook on filters: type: array items: $ref: '#/components/schemas/PhoneNumberCallRingingHookFilter' description: >- Optional filters to decide when to trigger the hook. Currently supports filtering by caller country code. do: type: array items: $ref: '#/components/schemas/PhoneNumberHookCallRingingDoItems' description: >- Only the first action will be executed. Additional actions will be ignored. required: - 'on' - do title: PhoneNumberHookCallRinging PhoneNumberHookCallEndingOn: type: string enum: - call.ending description: This is the event to trigger the hook on title: PhoneNumberHookCallEndingOn PhoneNumberCallEndingHookFilterType: type: string enum: - oneOf description: This is the type of filter - currently only "oneOf" is supported title: PhoneNumberCallEndingHookFilterType PhoneNumberCallEndingHookFilterKey: type: string enum: - call.endedReason description: >- This is the key to filter on - only "call.endedReason" is allowed for phone number call ending hooks title: PhoneNumberCallEndingHookFilterKey PhoneNumberCallEndingHookFilterOneOf: type: string enum: - assistant-request-failed - assistant-request-returned-error - assistant-request-returned-unspeakable-error - assistant-request-returned-invalid-assistant - assistant-request-returned-no-assistant - assistant-request-returned-forwarding-phone-number description: >- This is the array of assistant-request related ended reasons to match against title: PhoneNumberCallEndingHookFilterOneOf PhoneNumberCallEndingHookFilter: type: object properties: type: $ref: '#/components/schemas/PhoneNumberCallEndingHookFilterType' description: This is the type of filter - currently only "oneOf" is supported key: $ref: '#/components/schemas/PhoneNumberCallEndingHookFilterKey' description: >- This is the key to filter on - only "call.endedReason" is allowed for phone number call ending hooks oneOf: $ref: '#/components/schemas/PhoneNumberCallEndingHookFilterOneOf' description: >- This is the array of assistant-request related ended reasons to match against required: - type - key - oneOf title: PhoneNumberCallEndingHookFilter PhoneNumberHookCallEndingDo: oneOf: - $ref: '#/components/schemas/TransferPhoneNumberHookAction' - $ref: '#/components/schemas/SayPhoneNumberHookAction' description: This is the action to perform when the hook triggers title: PhoneNumberHookCallEndingDo PhoneNumberHookCallEnding: type: object properties: 'on': $ref: '#/components/schemas/PhoneNumberHookCallEndingOn' description: This is the event to trigger the hook on filters: type: array items: $ref: '#/components/schemas/PhoneNumberCallEndingHookFilter' description: >- Optional filters to decide when to trigger - restricted to assistant-request related ended reasons do: $ref: '#/components/schemas/PhoneNumberHookCallEndingDo' description: This is the action to perform when the hook triggers required: - 'on' title: PhoneNumberHookCallEnding ImportTwilioPhoneNumberDtoHooksItems: oneOf: - $ref: '#/components/schemas/PhoneNumberHookCallRinging' - $ref: '#/components/schemas/PhoneNumberHookCallEnding' title: ImportTwilioPhoneNumberDtoHooksItems ImportTwilioPhoneNumberDTO: type: object properties: fallbackDestination: $ref: '#/components/schemas/ImportTwilioPhoneNumberDtoFallbackDestination' description: >- This is the fallback destination an inbound call will be transferred to if: 1. `assistantId` is not set 2. `squadId` is not set 3. and, `assistant-request` message to the `serverUrl` fails If this is not set and above conditions are met, the inbound call is hung up with an error message. hooks: type: array items: $ref: '#/components/schemas/ImportTwilioPhoneNumberDtoHooksItems' description: >- This is the hooks that will be used for incoming calls to this phone number. smsEnabled: type: boolean default: true description: >- Controls whether Vapi sets the messaging webhook URL on the Twilio number during import. If set to `false`, Vapi will not update the Twilio messaging URL, leaving it as is. If `true` or omitted (default), Vapi will configure both the voice and messaging URLs. @default true twilioPhoneNumber: type: string description: These are the digits of the phone number you own on your Twilio. twilioAccountSid: type: string description: >- This is your Twilio Account SID that will be used to handle this phone number. twilioAuthToken: type: string description: >- This is the Twilio Auth Token that will be used to handle this phone number. twilioApiKey: type: string description: >- This is the Twilio API Key that will be used to handle this phone number. If AuthToken is provided, this will be ignored. twilioApiSecret: type: string description: >- This is the Twilio API Secret that will be used to handle this phone number. If AuthToken is provided, this will be ignored. name: type: string description: >- This is the name of the phone number. This is just for your own reference. assistantId: type: string description: >- This is the assistant that will be used for incoming calls to this phone number. If neither `assistantId`, `squadId` nor `workflowId` is set, `assistant-request` will be sent to your Server URL. Check `ServerMessage` and `ServerMessageResponse` for the shape of the message and response that is expected. workflowId: type: string description: >- This is the workflow that will be used for incoming calls to this phone number. If neither `assistantId`, `squadId`, nor `workflowId` is set, `assistant-request` will be sent to your Server URL. Check `ServerMessage` and `ServerMessageResponse` for the shape of the message and response that is expected. squadId: type: string description: >- This is the squad that will be used for incoming calls to this phone number. If neither `assistantId`, `squadId`, nor `workflowId` is set, `assistant-request` will be sent to your Server URL. Check `ServerMessage` and `ServerMessageResponse` for the shape of the message and response that is expected. server: $ref: '#/components/schemas/Server' description: >- This is where Vapi will send webhooks. You can find all webhooks available along with their shape in ServerMessage schema. The order of precedence is: 1. assistant.server 2. phoneNumber.server 3. org.server required: - twilioPhoneNumber - twilioAccountSid title: ImportTwilioPhoneNumberDTO CreateCustomerDTO: type: object properties: numberE164CheckEnabled: type: boolean default: true description: >- This is the flag to toggle the E164 check for the `number` field. This is an advanced property which should be used if you know your use case requires it. Use cases: - `false`: To allow non-E164 numbers like `+001234567890`, `1234`, or `abc`. This is useful for dialing out to non-E164 numbers on your SIP trunks. - `true` (default): To allow only E164 numbers like `+14155551234`. This is standard for PSTN calls. If `false`, the `number` is still required to only contain alphanumeric characters (regex: `/^\+?[a-zA-Z0-9]+$/`). @default true (E164 check is enabled) extension: type: string description: >- This is the extension that will be dialed after the call is answered. assistantOverrides: $ref: '#/components/schemas/AssistantOverrides' description: >- These are the overrides for the assistant's settings and template variables specific to this customer. This allows customization of the assistant's behavior for individual customers in batch calls. number: type: string description: This is the number of the customer. sipUri: type: string description: This is the SIP URI of the customer. name: type: string description: >- This is the name of the customer. This is just for your own reference. For SIP inbound calls, this is extracted from the `From` SIP header with format `"Display Name" `. email: type: string description: This is the email of the customer. externalId: type: string description: This is the external ID of the customer. title: CreateCustomerDTO SchedulePlan: type: object properties: earliestAt: type: string format: date-time description: >- This is the ISO 8601 date-time string of the earliest time the call can be scheduled. latestAt: type: string format: date-time description: >- This is the ISO 8601 date-time string of the latest time the call can be scheduled. required: - earliestAt title: SchedulePlan CallTransport: type: object properties: {} description: This is the transport of the call. title: CallTransport SubscriptionLimits: type: object properties: concurrencyBlocked: type: boolean default: false description: True if this call was blocked by the Call Concurrency limit concurrencyLimit: type: number format: double description: Account Call Concurrency limit remainingConcurrentCalls: type: number format: double description: >- Incremental number of concurrent calls that will be allowed, including this call title: SubscriptionLimits Call: type: object properties: type: $ref: '#/components/schemas/CallType' description: This is the type of call. costs: type: array items: $ref: '#/components/schemas/CallCostsItems' description: These are the costs of individual components of the call in USD. messages: type: array items: $ref: '#/components/schemas/CallMessagesItems' phoneCallProvider: $ref: '#/components/schemas/CallPhoneCallProvider' description: |- This is the provider of the call. Only relevant for `outboundPhoneCall` and `inboundPhoneCall` type. phoneCallTransport: $ref: '#/components/schemas/CallPhoneCallTransport' description: |- This is the transport of the phone call. Only relevant for `outboundPhoneCall` and `inboundPhoneCall` type. status: $ref: '#/components/schemas/CallStatus' description: This is the status of the call. endedReason: $ref: '#/components/schemas/CallEndedReason' description: This is the explanation for how the call ended. endedMessage: type: string description: >- This is the message that adds more context to the ended reason. It can be used to provide potential error messages or warnings. destination: $ref: '#/components/schemas/CallDestination' description: >- This is the destination where the call ended up being transferred to. If the call was not transferred, this will be empty. id: type: string description: This is the unique identifier for the call. orgId: type: string description: This is the unique identifier for the org that this call belongs to. createdAt: type: string format: date-time description: This is the ISO 8601 date-time string of when the call was created. updatedAt: type: string format: date-time description: >- This is the ISO 8601 date-time string of when the call was last updated. startedAt: type: string format: date-time description: This is the ISO 8601 date-time string of when the call was started. endedAt: type: string format: date-time description: This is the ISO 8601 date-time string of when the call was ended. cost: type: number format: double description: This is the cost of the call in USD. costBreakdown: $ref: '#/components/schemas/CostBreakdown' description: This is the cost of the call in USD. artifactPlan: $ref: '#/components/schemas/ArtifactPlan' description: >- This is a copy of assistant artifact plan. This isn't actually stored on the call but rather just returned in POST /call/web to enable artifact creation client side. analysis: $ref: '#/components/schemas/Analysis' description: >- This is the analysis of the call. Configure in `assistant.analysisPlan`. monitor: $ref: '#/components/schemas/Monitor' description: >- This is to real-time monitor the call. Configure in `assistant.monitorPlan`. artifact: $ref: '#/components/schemas/Artifact' description: >- These are the artifacts created from the call. Configure in `assistant.artifactPlan`. compliance: $ref: '#/components/schemas/Compliance' description: >- This is the compliance of the call. Configure in `assistant.compliancePlan`. phoneCallProviderId: type: string description: >- The ID of the call as provided by the phone number service. callSid in Twilio. conversationUuid in Vonage. callControlId in Telnyx. Only relevant for `outboundPhoneCall` and `inboundPhoneCall` type. campaignId: type: string description: This is the campaign ID that the call belongs to. assistantId: type: string description: >- This is the assistant ID that will be used for the call. To use a transient assistant, use `assistant` instead. To start a call with: - Assistant, use `assistantId` or `assistant` - Squad, use `squadId` or `squad` - Workflow, use `workflowId` or `workflow` assistant: $ref: '#/components/schemas/CreateAssistantDTO' description: >- This is the assistant that will be used for the call. To use an existing assistant, use `assistantId` instead. To start a call with: - Assistant, use `assistant` - Squad, use `squad` - Workflow, use `workflow` assistantOverrides: $ref: '#/components/schemas/AssistantOverrides' description: >- These are the overrides for the `assistant` or `assistantId`'s settings and template variables. squadId: type: string description: >- This is the squad that will be used for the call. To use a transient squad, use `squad` instead. To start a call with: - Assistant, use `assistant` or `assistantId` - Squad, use `squad` or `squadId` - Workflow, use `workflow` or `workflowId` squad: $ref: '#/components/schemas/CreateSquadDTO' description: >- This is a squad that will be used for the call. To use an existing squad, use `squadId` instead. To start a call with: - Assistant, use `assistant` or `assistantId` - Squad, use `squad` or `squadId` - Workflow, use `workflow` or `workflowId` squadOverrides: $ref: '#/components/schemas/AssistantOverrides' description: >- These are the overrides for the `squad` or `squadId`'s member settings and template variables. This will apply to all members of the squad. workflowId: type: string description: >- This is the workflow that will be used for the call. To use a transient workflow, use `workflow` instead. To start a call with: - Assistant, use `assistant` or `assistantId` - Squad, use `squad` or `squadId` - Workflow, use `workflow` or `workflowId` workflow: $ref: '#/components/schemas/CreateWorkflowDTO' description: >- This is a workflow that will be used for the call. To use an existing workflow, use `workflowId` instead. To start a call with: - Assistant, use `assistant` or `assistantId` - Squad, use `squad` or `squadId` - Workflow, use `workflow` or `workflowId` workflowOverrides: $ref: '#/components/schemas/WorkflowOverrides' description: >- These are the overrides for the `workflow` or `workflowId`'s settings and template variables. phoneNumberId: type: string description: >- This is the phone number that will be used for the call. To use a transient number, use `phoneNumber` instead. Only relevant for `outboundPhoneCall` and `inboundPhoneCall` type. phoneNumber: $ref: '#/components/schemas/ImportTwilioPhoneNumberDTO' description: >- This is the phone number that will be used for the call. To use an existing number, use `phoneNumberId` instead. Only relevant for `outboundPhoneCall` and `inboundPhoneCall` type. customerId: type: string description: >- This is the customer that will be called. To call a transient customer , use `customer` instead. Only relevant for `outboundPhoneCall` and `inboundPhoneCall` type. customer: $ref: '#/components/schemas/CreateCustomerDTO' description: >- This is the customer that will be called. To call an existing customer, use `customerId` instead. Only relevant for `outboundPhoneCall` and `inboundPhoneCall` type. name: type: string description: This is the name of the call. This is just for your own reference. schedulePlan: $ref: '#/components/schemas/SchedulePlan' description: This is the schedule plan of the call. transport: $ref: '#/components/schemas/CallTransport' description: This is the transport of the call. subscriptionLimits: $ref: '#/components/schemas/SubscriptionLimits' description: >- These are the subscription limits for the org at the time of the call. Includes concurrency limit information. required: - id - orgId - createdAt - updatedAt title: Call securitySchemes: bearer: type: http scheme: bearer description: Retrieve your API Key from [Dashboard](dashboard.vapi.ai). ``` ## SDK Code Examples ```python from vapi import Vapi client = Vapi( token="YOUR_TOKEN_HERE", ) client.calls.delete( id="id", ) ``` ```go package example import ( context "context" serversdkgo "github.com/VapiAI/server-sdk-go" client "github.com/VapiAI/server-sdk-go/client" option "github.com/VapiAI/server-sdk-go/option" ) func do() { client := client.NewClient( option.WithToken( "YOUR_TOKEN_HERE", ), ) request := &serversdkgo.DeleteCallDto{ Id: "id", } client.Calls.Delete( context.TODO(), request, ) } ```