LiveKit docs › Models › TTS › Additional models › Mistral AI

---

# Mistral TTS plugin guide

> How to use the Mistral TTS plugin for LiveKit Agents.

Available in:
- [x] Node.js
- [x] Python

## Overview

This plugin allows you to use [Voxtral](https://mistral.ai/news/voxtral-tts) as a TTS provider for your voice agents.

### Installation

Install the LiveKit Mistral AI plugin from PyPI or npm:

**Python**:

```shell
uv add "livekit-agents[mistralai]~=1.5"

```

---

**Node.js**:

```shell
pnpm add @livekit/agents-plugin-mistralai

```

### Authentication

The Mistral plugin requires a [Mistral AI API key](https://console.mistral.ai/api-keys).

Set `MISTRAL_API_KEY` in your `.env` file.

### Usage

Use Mistral TTS within an `AgentSession` or as a standalone speech generator. For example, you can use this TTS in the [Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md).

**Python**:

```python
from livekit.plugins import mistralai

session = AgentSession(
    tts=mistralai.TTS(
    ),
    # ... llm, stt, etc.
)

```

---

**Node.js**:

```typescript
import * as mistralai from '@livekit/agents-plugin-mistralai';

const session = new voice.AgentSession({
    stt: new mistralai.TTS({
    }),
    // ... llm, stt, etc.
});

```

### Parameters

This section describes some of the available parameters. See the [plugin reference](https://docs.livekit.io/reference/python/livekit/plugins/mistralai.md#livekit.plugins.mistralai.TTS) for a complete list of all available parameters.

- **`model`** _(TTSModels | string)_ (optional) - Default: `voxtral-mini-tts-2603`: Voxtral TTS model to use. To learn more, see [TTS model options](https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03).

- **`voice`** _(TTSVoices | string)_ (optional) - Default: `en_paul_neutral`: Voxtral TTS voice to use.

- **`ref_audio`** _(str)_ (optional): Base64-encoded audio sample for zero-shot voice cloning. Mutually exclusive with `voice`.

- **`response_format`** _(RESPONSE_FORMAT)_ (optional): The audio format of synthesized speech, between `mp3`, `wav`, `pcm`, `opus` or `flac`. Defaults to `mp3`.

## Additional resources

The following resources provide more information about using Mistral with LiveKit Agents.

- **[Mistral docs](https://docs.mistral.ai/capabilities/audio/)**: Mistral audio documentation.

- **[Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md)**: Get started with LiveKit Agents and Mistral TTS.

---

This document was rendered at 2026-06-07T11:35:50.414Z.
For the latest version of this document, see [https://docs.livekit.io/agents/models/tts/mistralai.md](https://docs.livekit.io/agents/models/tts/mistralai.md).

To explore all LiveKit documentation, see [llms.txt](https://docs.livekit.io/llms.txt).