LiveKit

Overview

LiveKit Agents is a real-time framework for building voice, video, and multimodal AI agents. It runs on top of LiveKit's WebRTC media transport, giving agents low-latency, reliable connections to users even on unstable networks, and ships with built-in turn detection, interruption handling, and telephony support.

An AgentSession orchestrates the speech-to-text, LLM, and text-to-speech components for each conversation. Soniox plugs in as two of these components:

• soniox.STT transcribes incoming user audio in real time using the Soniox real-time STT API.
• soniox.TTS synthesizes the LLM's responses into speech using the Soniox real-time TTS API.

For more details on how LiveKit Agents work, check the LiveKit Agents documentation.

Installation

Install the Soniox plugin for LiveKit Agents:

pip install livekit-plugins-soniox

You will also need to set up your Soniox API key as an environment variable:

export SONIOX_API_KEY=<your_soniox_api_key>

You can obtain a Soniox API key by signing up at the Soniox Console.

Services