Skip to main content

MiniMax TTS plugin guide

How to use the MiniMax TTS plugin for LiveKit Agents.

On this page

Available inPython

Overview

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

Installation

Install the plugin from PyPI:

pip install "livekit-agents[minimax]~=1.8"

Authentication

The MiniMax plugin requires a MiniMax API key .

Set MINIMAX_API_KEY in your .env file.

Usage

Use MiniMax 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 minimax
session = AgentSession(
tts=minimax.TTS(
),
# ... llm, stt, etc.
)

Parameters

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

modelTTSModel | stringDefault: speech-02-turbo

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

voiceTTSVoice | stringDefault: socialmedia_female_2_v1

MiniMax TTS voice to use.

emotionTTSEmotion | stringDefault: None

Control emotional tone for speech. Valid values are happy, sad, angry, fearful, disgusted, surprised, neutral, and fluent. Only speech-2.6-* models accept fluent.

speedfloat

Speech speed where higher values speak faster. Range is 0.5 to 2.0.

pronunciation_dictdict[str, list[str]]

Defines the pronunciation rules for specific characters or symbols. Read more in the MiniMax API documentation .

text_normalizationboolDefault: false

Set to true to enable text normalization. This improves the pronunciation of numbers and dates, but adds a small amount of latency. Read more in the MiniMax API reference .

Additional resources

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