LiveKit text to speech

Use Speechmatics text-to-speech voices in your LiveKit voice agents.

Give your LiveKit voice agent natural, expressive speech with Speechmatics TTS.

Installation

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

Usage

from livekit.agents import AgentSession
from livekit.plugins import speechmatics

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

Configuration

Parameter	Type	Default	Description
voice	string	"sarah"	Voice model to use
api_key	string	env var	Speechmatics API key (defaults to SPEECHMATICS_API_KEY)

For available voices and detailed TTS options, see the Text to speech quickstart.

Next steps

• Quickstart — Build a complete voice agent
• Speech to text — Configure STT options