SignSphere makes video content accessible to deaf and hard-of-hearing viewers by generating sign language interpretation alongside the video they're already watching. No separate player, no waiting for a human interpreter.
How it works
- The extension picks up the active YouTube caption track as the video plays.
- Captions are segmented and mapped to a sign gloss representation.
- A rendered interpreter is overlaid next to the player, in sync with playback.
The hard part was latency. Interpretation that lags behind the audio is worse than none at all, so the pipeline buffers ahead of the playhead and renders in advance rather than reacting frame by frame.