Transcribe audio and video

Pick an audio or video file and get the text to copy, or captions as SRT. The AI (Whisper) runs on your own device, so the file never leaves it.

Choose or drop an audio or video fileMP3, MP4, M4A, WAV, OGG/Opus, WebM · stays on your device

Spoken language Quality

The first time, your browser downloads the AI model (once; it is kept afterwards). A computer is much faster than a phone.

Everything stays on your device: transcription runs in the browser. Nothing is uploaded or stored.

How to use

Podcast show notes. Transcribe the episode, then pull quotes and timestamps for the description.
Meeting or lecture recording. Get searchable notes from a recorded call without sending it to a cloud service.
YouTube and TikTok captions. Download the SRT and upload it in YouTube Studio or your editor — more accessible, easier to find.

A clean recording gives better text: close to the mic, no background music.
Check names and jargon before you publish.
If people switch languages, choose the main one.
Very long videos may run out of memory on a phone: split them in the Video editor first.

Is my file uploaded?

No. The AI model is downloaded to your browser and the transcription happens on your device. The file never leaves it.

Which formats work?

Anything your browser can play: MP3, MP4, M4A, WAV, OGG and Opus (WhatsApp voice notes), WebM, FLAC, AAC. MOV and MKV depend on the browser.

Does it work offline?

After the model has been downloaded once, transcription itself runs on your device; you only need the page to be open.

Is it accurate?

Usually good with clear audio, but noise, overlapping speakers and names cause mistakes. Always proofread.

Is it free?

Yes — no account, no minute limit.