Real-time voice AI agents
LiveKit Agents is a Python framework used to develop real-time audio and video artificial intelligence agents. It enables developers to create low-latency voice interactions, making it easier to create AI systems that respond human-like.
Updates
- September 16, 2026: Stars 14,122 → 14,221, latest release livekit-agents@1.8.2 (September 15, 2026).
- September 11, 2026: Stars 14,020 → 14,122, latest release livekit-agents@1.8.1 (September 10, 2026).
- September 5, 2026: Stars 13,186 → 14,020, latest release livekit-agents@1.8.0 (September 5, 2026).
- August 27, 2026: Stars 13,110 → 13,186, latest release livekit-agents@1.7.1 (August 27, 2026).
What you get
- Creates vocal interactions that produce human-like responses.
- WebRTC media server is fully compatible with LiveKit.
- Supports phone calls and multi-mode data exchange.
Installation
pip install "livekit-agents[openai,deepgram,cartesia]"npx skills add livekit/agent-skills --skill livekit-agentsIf you don't write code
I want to develop an artificial intelligence agent that can interact with real-time voice using LiveKit Agents. Create an initial template using the Agent, AgentSession, and JobContext structure required for the agent to listen to the user, understand the ends of the conversation, and respond using the specified tools. Explain how I can configure the STT, LLM and TTS required for voice responses and how I can define functional tools on this agent.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-08-04: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.