On-device AI
Audio & Video to Text
Turn lectures, interviews, videos and voice notes into text, and download SRT subtitles ready for YouTube, in 99 languages.
1Choose an audio or video file (MP3, M4A, WAV, MP4 and more).
Your data never leaves your device
Related tools
How to use this tool
- 1
Choose an audio or video file (MP3, M4A, WAV, MP4 and more).
- 2
Pick the spoken language or let it be detected, then press Transcribe.
- 3
Fix any line if needed, then copy the text or download it as TXT, SRT or VTT subtitles.
Frequently Asked Questions
No. The speech recognition model (Whisper) runs inside your browser. The model itself is downloaded once; your file never leaves your device, so it is safe for confidential meetings and interviews.
No minute limits and no subscription. The only limit is your device: an hour of audio usually takes a few minutes on a recent computer and longer on a phone. Files up to 1 GB are supported.
Clear speech in common languages comes out well. For the best result pick the language yourself, choose Accurate, and use a recording with little background noise. You can correct any line before downloading.
Download the SRT file, then in YouTube Studio open the video, go to Subtitles, add a language and choose Upload file. SRT also works in most video editors and players.
Yes. Tick "Translate the speech into English" and the text comes out in English whatever language is spoken.