Transcribe audio and video to text
Turn speech into text with on-device AI.
Processed on your deviceHow to Transcribe audio & video
- 1
Open an audio or video file.
- 2
Choose the spoken language, or leave it on auto-detect.
- 3
Click Transcribe, then copy the text or download it as TXT, Word, PDF or subtitles.
Frequently asked questions
Is it really private?
Yes. The Whisper speech model runs inside your browser. Your recording is never uploaded.
How long does it take?
The first run downloads the model, then it's cached. On a modern laptop, transcription runs at about real-time or faster, and faster still on computers with WebGPU.
Which languages work?
Whisper understands around 100 languages, including English, Spanish, Portuguese, French, German, Indonesian, Swahili, Hindi and Arabic. It can also translate speech into English.