Drop a clip → get word-synced Final Fantasy VII dialog-box captions burned in.
100% in your browser. Your video is never uploaded anywhere.
Runs on Whisper (speech-to-text) + ffmpeg.wasm, all client-side.
First run downloads the models (~40–80 MB), cached after that.
Rendering happens in real time, so a 30-second clip takes ~30 seconds plus encoding.
Works best in Chrome / Edge on desktop.