> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.vapi.ai/providers/transcriber/overview/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vapi.ai/_mcp/server. # Transcribers (Speech-to-text) > Reference of every speech-to-text provider Vapi supports, including provider IDs and where to configure each one. This page lists the speech-to-text (STT) providers Vapi supports, with each provider's ID. The transcriber converts the caller's speech to text for your voice agent. You select one by setting `transcriber.provider` and `transcriber.model` on an assistant. See [Create Assistant](/api-reference/assistants/create) in the API reference. Language coverage and automatic detection behavior can vary by model within the same provider. Review the provider page before choosing a model and language combination. ## Quick reference The provider string is the exact value you pass in `transcriber.provider`. | Provider | Provider string | | ------------------------------------------------------------------ | --------------- | | [AssemblyAI](/providers/transcriber/assembly-ai#speech-to-text) | `assembly-ai` | | [Azure](/providers/transcriber/azure#speech-to-text) | `azure` | | [Cartesia](/providers/transcriber/cartesia#speech-to-text) | `cartesia` | | [Deepgram](/providers/transcriber/deepgram#speech-to-text) | `deepgram` | | [ElevenLabs](/providers/transcriber/elevenlabs#speech-to-text) | `11labs` | | [Gladia](/providers/transcriber/gladia#speech-to-text) | `gladia` | | [Google](/providers/transcriber/google#speech-to-text) | `google` | | [OpenAI](/providers/transcriber/openai#speech-to-text) | `openai` | | [Soniox](/providers/transcriber/soniox#speech-to-text) | `soniox` | | [Speechmatics](/providers/transcriber/speechmatics#speech-to-text) | `speechmatics` | | [xAI](/providers/transcriber/xai#speech-to-text) | `xai` | ## Related #### [Create an assistant](/api-reference/assistants/create) Set `transcriber.provider` and `transcriber.model` in the API. > Look up the speech-to-text providers Vapi supports and their IDs ## Docs - [AssemblyAI](https://docs.vapi.ai/providers/transcriber/assembly-ai.md): Configure AssemblyAI speech models, multilingual transcription, language steering, and prompting for a Vapi assistant. - [Azure](https://docs.vapi.ai/providers/transcriber/azure.md): Configure Azure Speech as your Vapi assistant's transcriber and select from the languages Vapi supports. - [Cartesia](https://docs.vapi.ai/providers/transcriber/cartesia.md): Configure Cartesia as your Vapi assistant's transcriber, including supported languages and transcription options. - [Deepgram](https://docs.vapi.ai/providers/transcriber/deepgram.md): Configure Deepgram as your Vapi assistant's transcriber, including supported models and languages. - [ElevenLabs](https://docs.vapi.ai/providers/transcriber/elevenlabs.md): Configure ElevenLabs as your Vapi assistant's transcriber, including Scribe models and supported languages. - [Gladia](https://docs.vapi.ai/providers/transcriber/gladia.md): Configure a Gladia transcription model, language, and provider settings for a Vapi assistant. - [Google](https://docs.vapi.ai/providers/transcriber/google.md): Configure Google as your Vapi assistant's transcriber, including Gemini transcription models and supported languages. - [OpenAI](https://docs.vapi.ai/providers/transcriber/openai.md): Configure OpenAI as your Vapi assistant's transcriber, including transcription models and supported languages. - [Soniox](https://docs.vapi.ai/providers/transcriber/soniox.md): Connect Soniox to a Vapi assistant and configure the stt-rt-v5 real-time speech-to-text model for low-latency, multilingual transcription and endpointing. - [Speechmatics](https://docs.vapi.ai/providers/transcriber/speechmatics.md): Configure Speechmatics as your Vapi assistant's transcriber and review setup guidance and supported options. - [xAI](https://docs.vapi.ai/providers/transcriber/xai.md): Configure xAI as your Vapi assistant's transcriber, including supported models, languages, and transcription options.