NETSHOW AVATAR LAB

Pick a character and drive a live talking face — with sample clips, your own microphone, or a live agent — rendered right in your browser.
—
loading…
idle
composite

Drive the face

Fixture clips $0 — repo voice samples
Microphone your voice drives the face — nothing is sent anywhere
Live agent real Realtime session via the voice sidecar — uses the shared mint budget
off
barge-in
interrupt resistance 0.80
State pad manual state preview
Tuning
viseme delay 70 ms
sensitivity -46 dB floor
motion 1.00
level—
fps—
mouth onset—
top viseme—

Engine: AnalyserNode RMS jaw + HeadAudio MFCC visemes (MIT, vendored, in-browser). Photo frames: gpt-image-2 identity edits, one-time generation. No per-minute vendor. No server GPU.

Also on this box

Avatar QC bench /alive-site/avatar-admin.html · operator QC bench

The whole face roster on one screen — the hybrid vector portraits, the Alive cast and the photo-real set, in three labelled groups — with the state, size and tuning controls beside them. Click a face and it mounts and drives right there, which is the fastest way to catch a bad line before a customer does. It is also where face-tuning.json is corrected and exported.

Worth knowing before you open it: the bench is free to drive, including its ▶ $0 talk control — but its voice copilot has a TALK button that opens a live voice session, and the bench labels that one billed usage. Nothing there spends until you press it.

Open the QC bench →