Skip to navigation
Assistants

Create Assistant

Creates a reusable assistant configuration containing the model, voice, transcriber, tools, prompts, and call behavior.

Authentication

AuthorizationBearer

Authenticate server-side requests with a private Vapi API key. Create or copy a key from the Vapi Dashboard and send it in the Authorization header as Bearer <token>. Keep private API keys out of client-side code and public repositories.

Request

This endpoint expects an object.
transcriberobjectOptional
These are the options for the assistant's transcriber.
modelobjectOptional
These are the options for the assistant's LLM.
voiceobjectOptional
These are the options for the assistant's voice.
firstMessagestringOptional

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.

firstMessageInterruptionsEnabledbooleanOptionalDefaults to false

Set to true to allow the user to interrupt the assistant while it speaks the first message. Default is false.

firstMessageModeenumOptional

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’

Allowed values:
voicemailDetectionenum or objectOptional

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.

clientMessagesenumOptional

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.

serverMessagesenumOptional

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.

maxDurationSecondsdoubleOptional10-43200

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)

backgroundSoundenum or stringOptional
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.
modelOutputInMessagesEnabledbooleanOptional

This determines whether the model’s output is used in conversation history rather than the transcription of assistant’s speech.

@default false

transportConfigurationslist of objectsOptional
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.
observabilityPlanobjectOptional
This is the plan for observability of assistant's calls. Currently, only Langfuse is supported.
credentialslist of objectsOptional
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.
hookslist of objectsOptional
This is a set of actions that will be performed on certain events.
namestringOptional<=40 characters
This is the name of the assistant. This is required when you want to transfer between assistants in a call.
voicemailMessagestringOptional<=1000 characters
This is the message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up.
endCallMessagestringOptional<=1000 characters
This is the message that the assistant will say if it ends the call. If unspecified, it will hang up without saying anything.
endCallPhraseslist of stringsOptional
This list contains phrases that, if spoken by the assistant, will trigger the call to be hung up. Case insensitive.
compliancePlanobjectOptional
Compliance settings for the assistant, including HIPAA and PCI behavior, security filtering, and recording consent.
metadataobjectOptional
This is for metadata you want to store on the assistant.
backgroundSpeechDenoisingPlanobjectOptional

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
artifactPlanobjectOptional

This is the plan for artifacts generated during assistant’s calls. Stored in call.artifact.

startSpeakingPlanobjectOptional

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.
stopSpeakingPlanobjectOptional

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.
monitorPlanobjectOptional

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.
credentialIdslist of stringsOptional
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.
serverobjectOptional

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
keypadInputPlanobjectOptional
Configuration for collecting and processing DTMF keypad input during calls.
analysisPlanobjectOptionalDeprecated

This is the plan for analysis of assistant’s calls. Stored in call.analysis.

Response

idstring
This is the unique identifier for the assistant.
orgIdstring
This is the unique identifier for the org that this assistant belongs to.
createdAtdatetime

This is the ISO 8601 date-time string of when the assistant was created.

updatedAtdatetime

This is the ISO 8601 date-time string of when the assistant was last updated.

transcriberobjectOptional
These are the options for the assistant's transcriber.
modelobjectOptional
These are the options for the assistant's LLM.
voiceobjectOptional
These are the options for the assistant's voice.
firstMessagestringOptional

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.

firstMessageInterruptionsEnabledbooleanOptionalDefaults to false

Set to true to allow the user to interrupt the assistant while it speaks the first message. Default is false.

firstMessageModeenumOptional

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’

Allowed values:
voicemailDetectionenum or objectOptional

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.

clientMessagesenumOptional

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.

serverMessagesenumOptional

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.

maxDurationSecondsdoubleOptional10-43200

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)

backgroundSoundenum or stringOptional
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.
modelOutputInMessagesEnabledbooleanOptional

This determines whether the model’s output is used in conversation history rather than the transcription of assistant’s speech.

@default false

transportConfigurationslist of objectsOptional
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.
observabilityPlanobjectOptional
This is the plan for observability of assistant's calls. Currently, only Langfuse is supported.
credentialslist of objectsOptional
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.
hookslist of objectsOptional
This is a set of actions that will be performed on certain events.
latestVersionstring or nullOptional

This is the latest version label (e.g. v3) of the assistant in the version history. null while the org is not yet onboarded to versioning, or for assistants that have not yet been published under it.

modelDeprecationslist of objectsOptional

Read-only. Present only when a model this configuration uses is deprecated or retired in Vapi’s model deprecation registry, judged on the day of the response. Each entry names the slot (for example model or model.fallbackModels[1]), provider, stored model, and deprecation and retirement dates as YYYY-MM-DD in UTC. replacementStatus is available with a replacementModel when a replacement can be recommended, or manual-action-required with no replacement model when eligibility is unknown or no eligible replacement exists. manual-action-required can be transient when compliance context is unavailable; re-fetch before acting. HIPAA-required configurations, sparse drafts, and squads with unresolved assistant references currently require manual action. HIPAA requirements include the organization and assistant settings, including HIPAA with data retention. Recommendations reflect the response-time decision; they do not confirm a swap or authorize future execution. Examples: an available recommendation includes {"replacementStatus":"available","replacementModel":"gpt-5"}; a blocked recommendation includes {"replacementStatus":"manual-action-required"}. Ignored if sent back in a create or update request.

namestringOptional<=40 characters
This is the name of the assistant. This is required when you want to transfer between assistants in a call.
voicemailMessagestringOptional<=1000 characters
This is the message that the assistant will say if the call is forwarded to voicemail. If unspecified, it will hang up.
endCallMessagestringOptional<=1000 characters
This is the message that the assistant will say if it ends the call. If unspecified, it will hang up without saying anything.
endCallPhraseslist of stringsOptional
This list contains phrases that, if spoken by the assistant, will trigger the call to be hung up. Case insensitive.
compliancePlanobjectOptional
Compliance settings for the assistant, including HIPAA and PCI behavior, security filtering, and recording consent.
metadataobjectOptional
This is for metadata you want to store on the assistant.
backgroundSpeechDenoisingPlanobjectOptional

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
artifactPlanobjectOptional

This is the plan for artifacts generated during assistant’s calls. Stored in call.artifact.

startSpeakingPlanobjectOptional

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.
stopSpeakingPlanobjectOptional

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.
monitorPlanobjectOptional

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.
credentialIdslist of stringsOptional
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.
serverobjectOptional

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
keypadInputPlanobjectOptional
Configuration for collecting and processing DTMF keypad input during calls.
analysisPlanobjectOptionalDeprecated

This is the plan for analysis of assistant’s calls. Stored in call.analysis.