Privacy

Your files never leave your device

Transcription happens inside your browser using WebAssembly. The video or audio you drop in is decoded and processed locally. It is not uploaded to any server, not stored, and not shared.

What is downloaded

On first use your browser downloads the speech model (about 75 MB) from a public model host. That is code, not your data. It is cached locally, so later visits need no download and the tool works offline.

What we do not collect

No account, no email, no file names, no transcripts. There is nothing to sign up for and nothing for us to keep.

Advertising

The site may display ads to cover hosting costs. Ad networks may set their own cookies. They never receive your media files, because your media never leaves your device.

Verify it yourself

Open your browser's developer tools, go to the Network tab, and run the tool. You will see the one-time model download and nothing containing your audio.

Last updated: 16 September 2026.