AI · GitHub repo
LiveKit Agents
Open-source Python framework for building realtime voice and multimodal AI assistants
LiveKit Agents is an open-source framework designed to build programmable, server-side voice and multimodal AI participants. It coordinates real-time audio transport with plug-and-play speech-to-text, LLM, and text-to-speech providers alongside voice activity detection. It solves the hard parts of conversational AI, including low latency, interruption handling, and room-level media routing.
What it's for
- Build real-time voice bots for sales training and customer roleplay simulations
- Assemble custom voice assistants using modular STT, LLM, and TTS models
- Handle live conversational voice over WebRTC with automatic interruption detection
- Create multimodal agents that can process live video and audio feeds simultaneously
Features
- Modular plugin ecosystem for STT, LLM, and TTS providers like OpenAI, Deepgram, and Cartesia
- Built-in voice activity detection (VAD) and turn-taking handling
- LiveKit WebRTC infrastructure integration for low-latency audio and video delivery
- Support for multi-agent handoffs and warm transfers
- Interactive development testing using the LiveKit Agents Playground
Pricing
Open source. Free and open source under Apache-2.0; LiveKit Cloud provides paid managed infrastructure
Details
- Type
- GitHub repo
- Category
- AI
- Topic
- Voice AI
- Open source
- Yes
- Platforms
- Code library, Linux, macOS, Windows, Self-hosted
- For
- Developers building real-time conversational voice and video AI applications in Python
- Alternative to
- Vapi, Retell AI, Daily Bots
- Tags
- voice ai, webrtc, llm, agents, python, stt, tts
Why it was saved
- @prestonrhodes: Enables developers to quickly assemble low-latency voice bots using modular STT (Deepgram), LLM (OpenAI), and TTS (Cartesia) pipelines with built-in voice activity detection and interruption handling.
Compare
Related
Platform for building and deploying interactive voice AI agents.
Open-source emotive text-to-speech foundation model with low conversational latency.
A low-cost, open-source stack for building real-time AI voice assistants
Platform and SDK for building custom AI voice agents and smart devices
No-code platform to build, test, and deploy conversational voice AI agents
Open-source platform and framework for building autonomous AI agents
Updated