This repository contains example code and demo applications for LiveKit Agents, a suite of tools for building, deploying, and scaling real-time voice and video AI agents.
LiveKit Agents is a Python library that enables you to build intelligent conversational agents with speech, text, and media capabilities. This repository contains examples that demonstrate how to use various features of the library.
To use these examples, first clone the repository and then install the required dependencies:
git clone https://github.com/livekit-examples/python-agents-examples.git
cd python-agents-examples
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt- 🗣️ Speech and Voice Processing - Built-in STT, TTS, and VAD capabilities for natural conversations.
- 💬 Comprehensive LLM Support - Integrate with OpenAI, Anthropic, Google, and more.
- 📞 Telephony Integration - Make and receive SIP calls with your agents.
- 📊 Metrics and Monitoring - Track and analyze agent performance.
- 🔄 Real-time Processing - Stream audio, text, and video in real-time.
- 📱 Multi-modal Capabilities - Handle text, audio, and video simultaneously.
- 🌐 Multilingual Support - Transcribe and respond in multiple languages.
- 🧩 Extensible Plugin System - Add custom capabilities to your agents.
For full documentation of LiveKit Agents, visit https://docs.livekit.io/agents/
|
Basic agent that listens for user input and provides a response. |
An agent that continues speaking without being interrupted. |
|
Agent that triages patients based on symptoms and medical history. |
AI shopping assistant that helps find products based on user preferences. |
|
Agent that can make outbound phone calls and handle conversations. |
Agent that can switch between different languages during conversation. |
|
Compare different text-to-speech providers side by side. |
Transfer calls from an AI agent to a human operator seamlessly. |
|
Real-time speech transcription with high accuracy. |
Integrate with OpenAI's streaming API for natural conversations. |
|
Detect specific keywords in speech in real-time. |
Implement function calling capabilities in your agents. |
|
Complete lifecycle management for SIP calls. |
Maintain conversation context across interactions. |
|
Play audio files during agent interactions. |
Simple sound repeating demo for testing audio pipelines. |
|
Run transcription on Raspberry Pi hardware. |
Set up an agent to answer incoming SIP calls. |
|
An AI-powered assistant that can answer questions about what it sees. |
|
|
An agent that can answer questions about the LiveKit docs site. |