New: Text → Sign translator  ·  Try the live sign predictor.
Open dataset

Help us build the world's most diverse sign-language training set.

Record a few seconds of any sign from your webcam. We extract pose, hand, and face landmarks — never your face image — and add the sample to an open training pipeline that improves real-time recognition for everyone.

Start recording Try live predictor
50 × 1662 Frames × landmarks per sample
3 Sign systems: PSL · ASL · Custom
100% Private — no faces leave your device
Track Pose, hands, face — 1662 features per frame.
Standardize Resampled to a 50-frame fixed-length sequence.
Train Saved as drive-ready .npy samples and metadata.
Text → Sign Type a phrase, watch every word signed back.
Most needed now

Pick a goal — these signs need data to train the next model

Record anything you like, but focusing here moves the model fastest. Showing PSL

0signs at goal
0samples collected

Needs data now

Capture

Hold a sign 2–4s, or switch on Rapid capture to auto-record many takes.
REC
—
0.0s 0 frames
Ready to start
What sign are you recording? 50 × 1662
Reference clip PSL
Type a sign name to preview the canonical clip.
Frames captured 0