How to Build an AI Avatar Agent with HeyGen

Build a real-time avatar voice agent with LiveKit Agents and HeyGen LiveAvatar. In this tutorial, you will see how to add a synchronized face to a LiveKit voice agent, connect the first-party LiveAvatar plugin, and publish avatar video over WebRTC. Sign up for LiveKit Cloud: https://cloud.livekit.io/signup?utm_source=youtube&utm_medium=video&utm_campaign=devrel&utm_content=OTQh2gPAMOk This walkthrough covers the LiveKit avatar architecture, how LiveAvatar joins a LiveKit room as a participant, how the avatar consumes your agent's audio output, and how to start an `AvatarSession` before your `AgentSession`. You will also see how sandbox mode works, how to choose video quality, and how to use the same STT, LLM, and TTS pipeline you already have in LiveKit Agents. By the end, you will know how to build a voice agent avatar for product demos, customer support, tutoring, onboarding, and interactive AI experiences that need both voice and video. 📚 Resources 📚 LiveAvatar by HeyGen docs: https://docs.livekit.io/agents/models/avatar/plugins/liveavatar/?utm_source=youtube&utm_medium=video&utm_campaign=devrel&utm_content=OTQh2gPAMOk Agent docs: https://docs.livekit.io/agents/?utm_source=youtube&utm_medium=video&utm_campaign=devrel&utm_content=OTQh2gPAMOk 🤝 Join the Community: https://community.livekit.io/?utm_source=youtube&utm_medium=video&utm_campaign=devrel&utm_content=OTQh2gPAMOk #livekit #ai #voiceai