Build apps that can
see, hear, and speak
The open source framework and cloud platform
for voice, video, and physical AI agents.
Powering billions of calls in production for:
Simple and Powerful APIs
Quickly build voice agents
1session = AgentSession(2 stt=deepgram.STT(),3 llm=openai.LLM(model="gpt-4o"),4 tts=cartesia.TTS(),5 vad=silero.VAD.load(),6 turn_detection=MultilingualModel(),7)
1
Voice AI quickstartBuild a simple voice agent with Python in less than 10 minutes.
Voice agent starter appsBring your agent to life through a web or mobile app.
Integrate with telephonyEnable your voice agent to make or take phone calls.
Deploy to LiveKit CloudRun your agents on LiveKit's global realtime infrastructure.
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
Chosen by Innovators
From startups to industry giants
Ready to build?
Start building your realtime application 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