Speech to Text
Turn recordings, meetings and videos into text and subtitles — the AI runs on your own device.
- Processed locally — your files never leave your device
- Free, no sign-up
- No file limits
How to use Speech to Text
- 1
Drop an audio or video file.
- 2
Choose the spoken language and accuracy.
- 3
Copy the text or download TXT, SRT or VTT subtitles.
Features
- Whisper AIOpenAI's open speech model, running locally in your browser.
- SubtitlesExport timed SRT or VTT files for YouTube, Premiere or CapCut.
- Truly privateInterviews and meetings are transcribed without leaving your computer.
Frequently asked questions
How accurate is it?
Very good for clear speech. Choose “Accurate” for noisy recordings or accents; it downloads a larger model once.
How long does it take?
Usually faster than real time on a modern computer; long files take longer on phones.
Is my audio uploaded?
No. The model is downloaded to your browser and runs there.