Speech to Text
Transcribe an audio or video file into text or subtitles (SRT, VTT) with Whisper, on your device: a meeting, an interview, a voice message, in 99 languages
Drop an audio or video file here or click to browse
A recording, a voice message, a meeting, a video… Nothing is uploaded.
Transcript
Click a time to play from there, or a sentence to correct it before you copy or download.
Duration
Words
Transcribed in
Speed (× real time)
Transcribe
Whisper, OpenAI's speech recognition model, runs on your device. It is downloaded the first time, then kept in your browser until you forget it.
Model
Whisper base, 146 MB.
A few times faster than the audio lasts on a computer, slower on a phone.
Whisper small, 254 MB.
Fewer mistakes, better names and punctuation, but about three times slower.
Output
Translated as it's transcribed: rougher than a translator, best with the accurate model.