Build voice, video, and physical AI agents
An open source framework and developer platform for building, testing, deploying, scaling, and observing agents in production.
Powering billions of calls in production for:
OpenAI built ChatGPT’s Advanced Voice on LiveKit Cloud, used by millions of users around the world every day.
Run millions of concurrent calls
Automatic turn detection and interruption handling
Deploy and scale agents with LiveKit Cloud
Simple and Powerful APIs
Quickly build voice agents
1session = AgentSession(2stt="deepgram/nova-3",3llm="google/gemma-4-31b-it",4tts="cartesia/sonic-3",5turn_detection=MultilingualModel()6)
1
Voice AI quickstartBuild a simple voice agent with Python or Node.js in less than 10 minutes.
Try it out
Voice agent starter appsBring your agent to life through a web or mobile app.
Try it out
Integrate with telephonyEnable your voice agent to make or take phone calls.
Try it out
Deploy to LiveKit CloudRun your agents on LiveKit's global realtime infrastructure.
Try it out
Developer platform
The complete stack for Voice AI
Open source framework to build and test agents
Inference gateway to access TTS, LLM, and STT models
Cloud platform for deploying and scaling agents
Phone numbers and SIP integrations for telephony
Full-stack observability for every agent session
How it works
1
2
3
4
Built for scale
Enterprise grade
infrastructure
GDPR ✓
SOC 2 Type 2 ✓
HIPAA ✓
1.00%
Uptime
1000ms
Global latency
1,000+
Developers
2,500,000,000+
Calls annually
1+
Regions globally
Ready to build?
Start building a voice AI agent with a free account. Reach out to us if you're interested in custom pricing.
No credit card required • 1,000 free agent session minutes monthly
