Resemble AI TTS integration guide

Overview

Resemble AI provides natural and human-like text-to-speech. You can use the Resemble AI TTS plugin for LiveKit Agents to build your voice AI applications.

Quick reference

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

Installation

Install the plugin from PyPI:

pip install "livekit-agents[resemble]~=1.0"

Authentication

The Resemble AI plugin requires a Resemble AI API key.

Set RESEMBLE_API_KEY in your .env file.

Usage

Use Resemble AI 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 resemble

session = AgentSession(
   tts=resemble.TTS(
      voice_uuid="55592656",
   )
   # ... llm, stt, etc.
)

Parameters

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

Customizing pronunciation

Resemble AI supports custom pronunciation with Speech Synthesis Markup Language (SSML), an XML-based markup language that gives you granular control over speech output. With SSML, you can leverage XML tags to craft audio content that delivers a more natural and engaging listening experience. To learn more, see SSML.

Additional resources

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

Python package

The livekit-plugins-resemble package on PyPI.

Plugin reference

Reference for the Resemble AI TTS plugin.

Resemble AI docs

Resemble AI docs.

Voice AI quickstart

Get started with LiveKit Agents and Resemble AI TTS.