Transcribe audio or video into an SRT file. Speech recognition runs locally with Whisper — the file never leaves your device.
Running on this device
Output
SRT
Upload
None
Model
Whisper (local)
This page is missing the security headers the speech model needs. Reload the page; if it persists, the server is not sending Cross-Origin-Opener-Policy and Cross-Origin-Embedder-Policy for this route.