LiveKit

LiveKit is an open source framework and developer platform for building, testing, deploying, scaling, and observing voice, video, and physical AI agents in production. It provides a complete stack for Voice AI including an open source framework to build and test agents, an inference gateway to access TTS, LLM, and STT models, a cloud platform for deploying and scaling agents, phone numbers and SIP integrations for telephony, and full-stack observability for every agent session. LiveKit supports running millions of concurrent calls with automatic turn detection and interruption handling, and is used by companies like OpenAI, Tesla, and Spotify. The platform offers simple and powerful APIs, with quickstart guides for building voice agents in Python or Node.js, integrating with telephony, and deploying to LiveKit Cloud.

Key Features

• Open source framework for building voice, video, and physical AI agents
• Inference gateway for TTS, LLM, and STT models
• Cloud platform for deployment and scaling
• Telephony integration with phone numbers and SIP
• Full-stack observability for agent sessions
• Automatic turn detection and interruption handling
• Global realtime infrastructure with low latency

Who It's For

LiveKit is designed for developers building AI-powered voice, video, or robotics applications, from startups to large enterprises.

Key Benefits

• Open source framework with flexible architecture
• Supports millions of concurrent calls
• Global low-latency realtime infrastructure
• Enterprise-grade compliance (GDPR, SOC 2, HIPAA)