Any recording, into 語.
Drop in an audio or video file and get the transcript back. No length limit, no account, and the recording never leaves your computer.
Runs on your machine · No upload · No length cap
Drop an audio or video file
MP3, WAV, M4A, MP4, MOV — any length
質問s
Is there a length limit?
No. Because the transcription runs on your own machine there is no server cost for us to cap, so a two-hour recording works the same as a two-minute one. Long files simply take longer to process.
Does my recording get uploaded?
Never. The model is downloaded to your browser once and then everything happens locally. You can disconnect from the internet after the model loads and the tool still works.
Can it tell speakers apart?
Not in the browser. Speaker identification needs a second model that is too heavy to run on a web page. The Yaps desktop app does this, labelling each speaker through an interview or meeting.
Which files can I use?
MP3, WAV, M4A, FLAC, OGG, and the audio from most MP4 and MOV files. If your browser cannot open a file, exporting it as MP3 first always works.
How long does a long recording take?
On a recent laptop with WebGPU, transcription runs several times faster than real time, so an hour of audio typically finishes in a few minutes. Older machines fall back to a slower path.
Now find out who said what.
Speaker-labelled transcripts for interviews and meetings.
macOS 13.0 以降が必要 (Apple Silicon を推奨)