Subtitle Generator

Local Whisper speech recognition · files never uploaded · export SRT / VTT

The Whisper model runs entirely inside your browser: files never leave your device. The model is downloaded on first use (served from our own infrastructure, cached automatically afterwards). GPU acceleration via WebGPU is enabled when available, otherwise falls back to CPU (slower).

Drop your file here

or click to browse

Local Whisper · files never uploaded · model cached by your browser