- FULL mode — HeyGen manages the end-to-end conversation (STT, LLM, TTS, turn-taking, memory, and contexts). Bring a prompt and a voice agent and you have a talking, listening avatar.
- LITE mode — you keep your own agent/LLM and use LiveAvatar for the avatar layer, wiring in integrations like the ElevenLabs Agent plugin.
Start here
LiveAvatar Overview
What LiveAvatar is, how it works, and how to get set up.
Building with Agents
Agent skills that assess your stack and build the integration end to end.
Sandbox Mode
Try LiveAvatar without wiring up production credentials.
API Reference
25+ endpoints for sessions, avatars, voices, contexts, LLM configs, and secrets.
Choose a mode
FULL Mode
HeyGen runs the full loop — lifecycle, voice settings, push-to-talk, custom LLM/TTS, and events.
LITE Mode
Bring your own agent — configuration, events, integrations, and the ElevenLabs Agent plugin.
Core concepts
Avatars
Pick and configure the avatar that fronts your conversation.
Voice Agents
Define the agent that listens and responds in real time.
Voices
Choose and tune the voice your avatar speaks with.
Contexts
Ground the conversation in the knowledge it needs.
Memory
Persist state across turns and sessions.
Secrets & Integrations
Connect external services and manage credentials.
Open the full LiveAvatar Documentation
API reference, guides, changelog, and OpenAPI specs → docs.liveavatar.com

