Neuphonic TTS integration guide

How to use the Neuphonic TTS plugin for LiveKit Agents.

Overview

Neuphonic provides hyper realistic realtime voice synthesis. You can use the Neuphonic TTS plugin for LiveKit Agents to build voice AI applications that sound realistic.

Quick reference

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

Installation

Install the plugin from PyPI:

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

Authentication

The Neuphonic plugin requires a Neuphonic API key.

Set NEUPHONIC_API_TOKEN in your .env file.

Usage

Use Neuphonic 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 neuphonic
session = AgentSession(
tts=neuphonic.TTS(
voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb"
),
# ... llm, stt, etc.
)

Parameters

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

voice_idstringRequired

ID of the voice to use for generation.

speedfloatOptionalDefault: 1

Speed of generated speech.

modelstringOptionalDefault: neu_hq

ID of the model to use for generation.

lang_codestringOptionalDefault: en

Language code for the generated speech.

Additional resources

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

Voice AI quickstart

Get started with LiveKit Agents and Neuphonic TTS.