Skip to main content

Speechmatics TTS plugin guide

How to use the Speechmatics TTS plugin for LiveKit Agents.

Available in
Python

Overview

This plugin allows you to use Speechmatics as a TTS provider for your voice agents. The plugin uses the Speechmatics preview TTS API and doesn't support streaming.

Quick reference

This section includes a brief overview of the Speechmatics TTS plugin. For more information, see Additional resources.

Installation

Install the plugin from PyPI:

uv add "livekit-agents[speechmatics]~=1.4"

Authentication

The Speechmatics plugin requires a Speechmatics API key.

Set SPEECHMATICS_API_KEY in your .env file.

Usage

Use Speechmatics 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 speechmatics
session = AgentSession(
tts=speechmatics.TTS(
voice="sarah",
),
# ... llm, stt, etc.
)

Parameters

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

voicestringOptionalDefault: sarah

Voice model to use for synthesis. Valid values: sarah, theo, and megan.

Additional resources

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

Voice AI quickstart

Get started with LiveKit Agents and Speechmatics TTS.