Work with recordings without sending them anywhere. The AI model downloads to your browser once and does the work on your device.
Turn a recording into text
Use Audio to text for interviews, lectures, meetings, voice notes and podcasts. It reads MP3, M4A, WAV and other audio, and the sound track of MP4, MOV, WebM and MKV videos, then gives you the transcript in paragraphs.
Make subtitles for a video
The same tool saves SRT and WebVTT subtitle files with start and end times for every line. Upload the SRT to YouTube Studio, or import it into your video editor, and correct any words the AI misheard.
What to expect
A small speech model runs in your browser, so the first run downloads about 91 MB and a recording takes roughly half its length to transcribe on a recent laptop. Clear speech works best; noise, music and people talking over each other lower accuracy. The limit is 60 minutes per file, or 20 on a phone.
Choose an audio tool
- Audio to text
Transcribe speech and make SRT subtitles.
Built by Faheem Riaz. Read how file privacy works or report a problem.