PS_AI_Agent

Go to file

j.foucher 224af6a27b WIP: Add ElevenLabsLipSyncComponent with spectral analysis lip sync

Real-time lip sync component that performs client-side spectral analysis
on the agent's PCM audio stream (ElevenLabs doesn't provide viseme data).

Pipeline: 512-point FFT (16kHz) → 5 frequency bands → 15 OVR visemes
→ ARKit blendshapes (MetaHuman compatible) → auto-apply morph targets.

Currently uses SetMorphTarget() which may be overridden by MetaHuman's
Face AnimBP — face animation not yet working. Debug logs added to
diagnose: audio flow, spectrum energy, morph target name matching.

Next steps: verify debug output, fix MetaHuman morph target override
(likely needs AnimBP integration like Convai approach).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-22 11:23:34 +01:00

.claude

Update memory: document v1.5.0 mic chunk size fix

2026-02-19 18:42:47 +01:00

ConvAI/Convai

Add convAI plugin

2026-02-19 12:44:26 +01:00

CPP/elevenlabs-convai-cpp-main

Ajout sample CPP

2026-02-21 20:48:10 +01:00

Unreal/PS_AI_Agent

WIP: Add ElevenLabsLipSyncComponent with spectral analysis lip sync