LiveKit
Open-source framework for voice and video AI agents

LiveKit is an open-source framework and managed platform for developing production-ready AI agents. It provides inference gateway access to speech-to-text, language models, and text-to-speech services from major providers, alongside a media server for voice and video communication.
Highlights
- Build agents in Python or Node.js with framework abstractions for conversation flow and turn management
- Deploy across web, mobile, desktop, and telephony channels without rewriting agent logic
- Automatic interruption handling and natural turn-taking detection reduce engineering overhead
- Self-hostable media server (open source) or use managed LiveKit Cloud for scalable inference
- Free tier includes 1,000 agent session minutes monthly; enterprise pricing available
LiveKit targets developers building voice assistants, customer service bots, and robotics applications—teams that need reliable real-time infrastructure without building media servers from scratch. The platform abstracts complexity so prototypes can scale quickly from testing to production voice and video interactions.
Comments(0)
Sign in to comment