Transcribe audio and video to text in your browser: English and 99 other languages, with SRT subtitles. Free, no sign-up, nothing uploaded.
Runs in your browser. Your files are never uploaded. How it works
Audio to Text turns speech in an audio or video file into text: interviews, meetings, lectures, podcasts, voice memos and videos. It runs entirely in your browser with open speech recognition models, so recordings never leave your device, and there is no sign-up, no limit and no fee.
How to transcribe audio
Choose an audio file (MP3, WAV, M4A…) or a video.
Choose the language: English (fast) for English, or the spoken language for anything else.
Click Transcribe. Text appears as it is recognised; fix anything in the box.
Download as text, SRT or VTT subtitles, or copy it.
Which option to choose
Your audio
Choose
First download
English, clear speech
English (fast)
27 MB
English with accents or noise
English (more accurate)
73 MB
Another language
That language
73 MB
Not sure / mixed
Detect the language
73 MB
Private by design
Your files are processed on your own device and never uploaded. See how it works.
To show the subtitles on any phone or app, burn the SRT into the video with Add Subtitles to Video.
Frequently asked questions
Is my audio uploaded?
No. The speech is recognised in your browser, on your device, and never sent anywhere. Meetings, interviews and voice notes stay private.
Which languages work?
English, plus 99 other languages including Chinese, Spanish, French, German, Japanese, Korean, Portuguese, Russian, Arabic and Hindi. Choose Detect the language if you are not sure.
How big is the download?
The first time, the English engine (27 MB) or the multi-language engine (73 MB) is downloaded and kept by your browser. After that it starts straight away.
How long does it take?
On a recent computer, about 1 to 3 minutes for an hour of audio with the fast English engine, and a few times longer with the multi-language one.
Can I get subtitles?
Yes. Download as SRT or VTT: every line has its start and end time, ready for YouTube, VLC or a video editor.
Can it translate?
Yes. Choose the spoken language (or Detect) and tick Translate to English.