> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sentivue.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice

> Providers that turn your workflow's responses into speech

The voice provider speaks the agent's responses. This is what the caller actually hears, so it shapes how the agent comes across more than any other setting.

Set your default voice on [Model Configurations](/talk/configurations/inference-providers), and override it per workflow where you need a different one. Credentials come from a [connection](/talk/configurations/connections).

## Supported providers

| Provider                                                       | Notes                                                           |
| -------------------------------------------------------------- | --------------------------------------------------------------- |
| [ElevenLabs](/talk/configurations/providers/elevenlabs)        | Also covers transcription                                       |
| [Cartesia](/talk/configurations/providers/cartesia)            | Also covers transcription                                       |
| [Deepgram](/talk/configurations/providers/deepgram)            | Also covers transcription                                       |
| [OpenAI](/talk/configurations/providers/openai)                | Also covers language models and transcription                   |
| [Azure Speech](/talk/configurations/providers/azure-speech)    | Needs a region. Also covers transcription                       |
| [Gemini TTS](/talk/configurations/providers/google-gemini-tts) | Gemini's own speech model. Supports a style prompt              |
| [Google Cloud](/talk/configurations/providers/google-cloud)    | Chirp 3 HD voices. Also covers transcription                    |
| [Inworld](/talk/configurations/providers/inworld)              |                                                                 |
| [Rime](/talk/configurations/providers/rime)                    |                                                                 |
| [Camb](/talk/configurations/providers/camb)                    |                                                                 |
| [MiniMax](/talk/configurations/providers/minimax)              | Needs a group ID. Also covers language models                   |
| [xAI](/talk/configurations/providers/xai)                      |                                                                 |
| [Sarvam](/talk/configurations/providers/sarvam)                | Indian languages. Also covers language models and transcription |

<Note>
  A provider listed here as covering more than one service needs only **one** connection.
</Note>

## Choosing a voice

Each provider ships a set of voices to choose from. If you want one that is not listed, enter its voice ID manually — check the provider's own voice library for the ID and which languages it supports.

Test the voice on a real call before going live. Voices that sound good in a provider's sample page can behave differently with your prompt, your pacing, and phone-quality audio.