🔊 PRODUCTION EL VOICE DEBUGGER

Audits the production ElevenLabs still-avatar transport, its personalized context, and tool readiness.
User-Agent:
Secure Context:
Protocol:

🌐EnvironmentPENDING

🔐Auth (whoami)PENDING

⚡EL Agent PrewarmPENDING

🎤Microphone AccessPENDING

🔈AudioContextPENDING

📡EL WebSocket TransportPENDING

⏱️Startup Deadline & RecoveryPENDING

🧰EL Tools ContractPENDING

🔐Signed Production SessionPENDING

⚡Voice Engine Pre-warmPENDING

🪪Voice Sheet / Dock UIPENDING

🎮GPU / Canvas HealthPENDING

🔇Echo Gate (AEC)PENDING

🔆Wake Lock (Screen-on)PENDING

🧠Personality InjectionPENDING

📦Context Items (profile + memory + modules)PENDING

📡 Live Client Telemetry — real sessions (last 80)

Events the chat voice engine persisted to state/voice/client-events.jsonl (hv_session / hv_openai / hv_tts / hv_lipsync / hv_error). This is what to copy when reporting a voice problem.

auto-refresh (5s)

🎙️ Chat EL Live-Avatar Controller — Production Probe

Uses the same HypatiaLiveAvatar controller as Chat: one microphone, one EL WebSocket, still avatar first. The moving renderer remains a separate opt-in probe and must never block voice.

Not running

Transportidle

Micidle

Rendererstill