Transcribe audio to text
Get the text of a recording, voice message, podcast or interview. Speech recognition runs in your browser: your audio stays with you.
Accepted: MP4, MOV, M4V, WEBM, MKV, AVI, 3GP, MPEG, MPG, WMV, FLV, MP3, WAV, M4A, AAC, OGG, OPUS, FLAC, WMA · Max 1.9 GB per file
Processed on your device — nothing is uploaded.
How to transcribe audio to text
Drop your audio file above (MP3, WAV, M4A, OGG, Opus…), or a video.
Pick the spoken language, then click Transcribe.
Fix the text if needed, copy it or download it as .txt (or as subtitles).
How it works
- Nothing leaves your device
- Whisper speech recognition runs in your browser. The model is downloaded once from our server, then cached.
- SRT, VTT or text
- SRT for editing software, YouTube and video players; VTT for the web; plain text in paragraphs for notes and minutes.
- Easy proofreading
- Fix each subtitle in a table while the video plays alongside. Adjust timings, shift everything at once, change the line length.
- For best results
- Pick the right language rather than automatic detection, and the Accurate model for noisy audio or several speakers. Seven languages are supported.
Related tools
- Automatic subtitlesCreate SRT or VTT subtitles for a video or audio file, fix them line by line, with nothing uploaded.
- Transcribe video to textGet a written copy of everything said in a lecture, a meeting or any MP4, MOV or WebM video.
- Add subtitles to videoWrite subtitles on your video (fonts, outline, banner) or import an .srt file.
- Video to MP3Extract the sound of any video (MP4, MOV, WebM, AVI, MKV) as MP3.
- OCR: image or PDF to textRead the text in a photo, screenshot or scanned PDF, then copy it or download it as TXT or a searchable PDF.