VIAxVOICE

Speaking face experimental v0.1

Local only: the face you load never leaves your browser and is never published. Drop a front-on portrait, type a line, and the real face speaks it — rendered as high-fidelity ASCII luminance, driven by the same viseme engine as the generative avatar.

This is the hybrid: a real face's luminance as the base, deformed live by text → visemes → mouth/brow/eye motion. No driving clip — the face wears the voice.

Load a face (neutral, front-on)
JPG / PNG — click or drop · stays on your device
loading model…

The face's mouth, brows and lids are moved by displacing the 468-landmark mesh from the viseme signals, then the photo is triangle-warped to follow — the reverse of the capture pipeline. Next: drive the timing from real Kokoro audio (the amplitude envelope) instead of a procedural pace, so it speaks any /synthesize line in perfect sync. — Kairos