video to text
Get a transcript of any video file — lectures, interviews, reels, meetings. The audio is extracted and transcribed right on your device.
How it works
Choose a video file. Your browser pulls out the audio track, converts it to 16 kHz mono (what the Whisper model expects) and transcribes it in sections, so you can watch the text appear as it goes. Nothing is uploaded — the video stays on your device.
When it's done, copy the text or download it as a plain .txt transcript, or as .srt / .vtt subtitles with timestamps.
Supported video formats
MP4 (H.264/AAC) and WebM work in all modern browsers. MOV files from iPhones usually work in Safari and Chrome. If a file won't open, it's usually an unusual audio codec — convert it to MP4 or extract the audio as MP3 first.
Very large videos (over about 500 MB) can run out of memory, especially on phones, because the browser has to read the whole file. For long recordings, export just the audio and transcribe that.
Tips for clean transcripts
Use the “better” model for interviews with several speakers or accents. Set the language manually if you know it — auto-detect can guess wrong in the first seconds, especially if a video starts with music.
The transcriber doesn't label speakers. If you need “Speaker 1 / Speaker 2”, add them while proof-reading.
What you get
- Plain text — copy it or download a .txt file.
- SRT and VTT subtitles with start and end times for every phrase.
- Optional English translation of speech in other languages.
Frequently asked questions
Is my video uploaded anywhere?
No. The audio is decoded and transcribed inside your browser. The only download is the AI model itself, from Hugging Face, the first time you use it.
How long does a 10-minute video take?
On a recent laptop with WebGPU, roughly a minute or two. On older computers or phones it can take as long as the video or longer.
Can I get subtitles instead of plain text?
Yes — download the SRT or VTT file and load it in your video editor or player.
Is my file uploaded to a server?
No. Everything runs in your browser. Only the Whisper AI model is downloaded (once) from Hugging Face and cached.
Is it free?
Yes — no sign-up, no minutes limit, no watermark. Your own device does the work, so there's nothing for us to charge for.