avatarlisted

# Avatar — VTuber Control ## Quick Start - Start system: ~/openclaw/scripts/start-avatar.sh - Stop system: ~/openclaw/scripts/stop-avatar.sh - Check health: curl -s http://localhost:8766/health ## Speaking ~/openclaw/scripts/avatar-speak.sh "text" [emotion] [output] Output controls where audio plays: - speakers — default system sink, people in the room hear it - mic — AvatarMic sink, people in Meet/calls hear it - both — both simultaneously Default output is speakers. ## Emotions neutral (default, eyes open), happy, sad, angry, relaxed, surprised Use neutral by default. happy closes the eyes (anime smile) — only use for genuine excitement. ## Infrastructure When avatar system is started, these are always available: - Virtual mic: AvatarMic.monitor (set as default source for Meet) - Virtual camera: /dev/video10 (captures renderer via CDP) - Virtual speaker sink: AvatarSpeaker (available for routing) The bot chooses per-speak where audio goes. Virtual mic and camera are always-on pipes. ## Service Control systemctl --user {start|stop|status|restart} avatar-control-server Renderer: cd ~/openclaw/avatar/renderer && npm run dev ## WebSocket API (Advanced) Port 8765 — must send identify first: { type: "identify", role: "agent", name: "@agentName@" } Commands after identify: - speak: { type: "speak", text: "Hello", emotion: "neutral", output: "mic" } - setExpression: { type: "setExpression", name: "happy", intensity: 1 } - setIdle: { type: "setIdle", mode: "breathin