Give your avatar a face that speaks β play a voice, mirror your own mic, or type a line, and watch three styles of living face blink, glance, raise a brow and mouth every word.
driveofffacewords
idle
β dB Β· β fps
basic colorsfacehaireyeslipsthe simple v1 faces β colors stick in this browser, nothing else changes
restylehairshirtpantsintensity
1 Β· ASCII / Unicode face β
Pure text glyphs. Mouth = viseme glyph, eyes blink + track gaze, thought bubble while thinking, transcript runs as a mouth-ribbon while speaking. Near-zero render cost β works anywhere text renders, even a terminal.
2 Β· Kinetic typography β
The transcript IS the face: the current word is the mouth β it stretches with the actual audio energy, pops on emphasis (!), drifts up as speech flows. Eyes live above the words. Needs a transcript lane (live agent or the word feed).
3 Β· Living sketch line β
Continuously-redrawn ink character β the stroke "boils" like hand-drawn animation (re-jittered ~11Γ/s). Parametric mouth (width/openness from visemes + energy), brows carry emotion, head tilts with the idle sway.