> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.vapi.ai/providers/voice/overview/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vapi.ai/_mcp/server.

# Voices (Text-to-speech)

> Find, preview, and use text-to-speech voices from any Vapi-supported provider, and look up a voiceId in the Vapi dashboard.

## Supported voice providers

The provider string is the exact value you pass in `voice.provider`.

| Provider                                                   | Provider string |
| ---------------------------------------------------------- | --------------- |
| [Vapi Voices](/providers/voice/vapi-voices#text-to-speech) | `vapi`          |
| [Azure](/providers/voice/azure#text-to-speech)             | `azure`         |
| [Cartesia](/providers/voice/cartesia#text-to-speech)       | `cartesia`      |
| [Deepgram](/providers/voice/deepgram#text-to-speech)       | `deepgram`      |
| [ElevenLabs](/providers/voice/elevenlabs#text-to-speech)   | `11labs`        |
| [Hume](/providers/voice/hume#text-to-speech)               | `hume`          |
| [Inworld](/providers/voice/inworld#text-to-speech)         | `inworld`       |
| [LMNT](/providers/voice/imnt#text-to-speech)               | `lmnt`          |
| [MiniMax](/providers/voice/minimax#text-to-speech)         | `minimax`       |
| [Neuphonic](/providers/voice/neuphonic#text-to-speech)     | `neuphonic`     |
| [OpenAI](/providers/voice/openai#text-to-speech)           | `openai`        |
| [Rime AI](/providers/voice/rimeai#text-to-speech)          | `rime-ai`       |
| [Smallest AI](/providers/voice/smallest-ai#text-to-speech) | `smallest-ai`   |
| [WellSaid](/providers/voice/wellsaid#text-to-speech)       | `wellsaid`      |
| [xAI](/providers/voice/xai#text-to-speech)                 | `xai`           |

## Find a voice in the dashboard

Vapi supports text-to-speech (TTS) voices from many providers. You choose a voice by setting the **provider** and **voiceId** on your assistant's **voice** configuration.

**Set an assistant's voice**

```bash
curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \
  -H "Authorization: Bearer $VAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice": {
      "provider": "PROVIDER",
      "voiceId": "VOICE_ID"
    }
  }'
```

For additional API configuration options, see [Create Assistant](/api-reference/assistants/create) in the API reference.

This page links to every supported provider and shows you how to find a **voiceId** in the dashboard.

The **Voice Library** in the [Vapi Dashboard](https://dashboard.vapi.ai) lists every
voice available to your organization. Browse and preview voices there, then copy a
voice's ID to use on an assistant.

Language support can vary by model and voice. Test your selected voice with the language you plan to use before publishing your assistant.

#### Browse and preview

In the [Vapi Dashboard](https://dashboard.vapi.ai), open **Resources**, then
**Voice Library**. Filter by **Provider** and search by name. Press play on a
voice to preview it.

#### Copy the voice ID

Click the copy icon on a voice to copy its ID.

#### Use it on an assistant

Open an assistant and click the edit (pencil) icon on the **Voice** card to
open **Voice Settings**. Choose the **Provider** and **Voice**, or paste the
copied ID under **Custom Voice ID**.

> **Tip**
>
> Some providers also let you use your own custom voice. See [Custom voices](/customization/custom-voices/custom-voice) for setup.

> **Tip**
>
> [Model Intelligence presets](/assistants/model-intelligence/presets) bundle a transcriber, model, and voice tuned for common use cases, so you can configure your assistant in one click.

> Find, preview, and use voices from any supported provider

## Docs

- [Vapi Voices](https://docs.vapi.ai/providers/voice/vapi-voices.md): Browse Vapi's curated voices, preview voice samples, review language support, and configure a Vapi voice on an assistant.
- [Legacy voice migration guide](https://docs.vapi.ai/providers/voice/vapi-voices/legacy-migration.md): Migrate from legacy Vapi Voices retired on March 1, 2026, seeing which voices were removed, the new human voice clones, and how to update your assistants.
- [Azure](https://docs.vapi.ai/providers/voice/azure.md): Configure Azure Speech as your Vapi assistant's text-to-speech provider and select an Azure voice.
- [Cartesia](https://docs.vapi.ai/providers/voice/cartesia.md): Configure Cartesia as your Vapi assistant's text-to-speech provider, including supported languages and voice options.
- [Deepgram](https://docs.vapi.ai/providers/voice/deepgram.md): Configure Deepgram as your Vapi assistant's text-to-speech provider and select a Deepgram Aura voice.
- [ElevenLabs](https://docs.vapi.ai/providers/voice/elevenlabs.md): Configure ElevenLabs as your Vapi assistant's text-to-speech provider and select an ElevenLabs voice.
- [Hume](https://docs.vapi.ai/providers/voice/hume.md): Connect Hume to Vapi to use its expressive Octave text-to-speech voices for your voice agent. Covers the models and how to select a voice in the API.
- [Inworld](https://docs.vapi.ai/providers/voice/inworld.md): Configure Inworld text-to-speech models, voices, languages, and synthesis options for a Vapi assistant.
- [LMNT](https://docs.vapi.ai/providers/voice/imnt.md): Configure an LMNT voice for a Vapi assistant and find its voice ID in the Vapi Voice Library.
- [MiniMax](https://docs.vapi.ai/providers/voice/minimax.md): Configure MiniMax as your Vapi assistant's text-to-speech provider, including voice models, voice IDs, and subtitle timing.
- [Neuphonic](https://docs.vapi.ai/providers/voice/neuphonic.md): Connect Neuphonic to Vapi to use its text-to-speech voices for your voice agent. Covers how to select a Neuphonic voice in the API.
- [OpenAI](https://docs.vapi.ai/providers/voice/openai.md): Configure OpenAI as your Vapi assistant's text-to-speech provider, including TTS models and voice selection.
- [Rime AI](https://docs.vapi.ai/providers/voice/rimeai.md): Configure a Rime AI model and voice for a Vapi assistant and find its voice ID in the Vapi Voice Library.
- [Smallest AI](https://docs.vapi.ai/providers/voice/smallest-ai.md): Connect Smallest AI to Vapi to use its low-latency text-to-speech voices for your voice agent. Covers the model and how to select a voice in the API.
- [WellSaid](https://docs.vapi.ai/providers/voice/wellsaid.md): Connect WellSaid Labs to Vapi to use its studio-quality text-to-speech voices for your voice agent. Covers the models and how to select a voice in the API.
- [xAI](https://docs.vapi.ai/providers/voice/xai.md): Configure xAI as your Vapi assistant's text-to-speech provider, including supported voices, languages, and voice options.