Mistral TTS plugin guide | LiveKit Documentation

Available in

Python

Overview

This plugin allows you to use Voxtral as a TTS provider for your voice agents.

Install the LiveKit Mistral AI plugin from PyPI:

pip install "livekit-agents[mistralai]~=1.5"

The Mistral plugin requires a Mistral AI API key.

Set MISTRAL_API_KEY in your .env file.

Use Mistral TTS within an AgentSession or as a standalone speech generator. For example, you can use this TTS in the Voice AI quickstart.

from livekit.plugins import mistralai

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

This section describes some of the available parameters. See the plugin reference for a complete list of all available parameters.

modelTTSModels | stringDefault: voxtral-mini-tts-2603

Voxtral TTS model to use. To learn more, see TTS model options.

voiceTTSVoices | stringDefault: en_paul_neutral

Voxtral TTS voice to use.

ref_audiostr

Base64-encoded audio sample for zero-shot voice cloning. Mutually exclusive with voice.

response_formatRESPONSE_FORMAT

The audio format of synthesized speech, between mp3, wav, pcm, opus or flac. Defaults to pcm.

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

The livekit-plugins-mistralai package on PyPI.

Reference for the Mistral TTS plugin.

Mistral audio documentation.

Get started with LiveKit Agents and Mistral TTS.