Video to text, transcribed in your browser
Turn the speech in a video into text. Drop an MP4, MOV, WebM or audio file and Whisper transcribes it right here, with timestamps, ready to copy or download as TXT, SRT or VTT subtitles. Free, and nothing is uploaded.
Your file is read by this browser tab and never sent anywhere. The first run downloads the AI model from Hugging Face and caches it, so later runs start faster and work offline.
How to convert a video to text
- Drop a video or audio file into the box, or click it to choose one. Nothing starts uploading, because nothing is uploaded.
- Leave the language on automatic, or pick it if you know it. Whisper Base is the quick choice; Whisper Small is worth the larger download for noisy or accented speech.
- Watch the transcript fill in, 30 seconds of audio at a time.
- Copy the text, or download it as a plain TXT file, an SRT file for YouTube, Premiere Pro or DaVinci Resolve, or a WebVTT file for the web.
Free video transcription without the upload
Online transcription services upload your video to their servers, run speech recognition there and send the text back. This page does the same work inside your browser. It reads the sound track with the browser's own media decoder, converts it to 16 kHz mono, and runs OpenAI Whisper through Transformers.js, on your graphics card through WebGPU where the browser supports it and on the CPU otherwise.
That matters when the recording is an interview under embargo, a client call, a deposition or anything else you would rather not hand to a third party. You can check it yourself: once the model has downloaded, turn off Wi-Fi and run another file.
Video to text, SRT or VTT: which output you need
- TXT for reading, quoting, show notes, blog posts or pasting into an AI assistant. Tick "Timestamps in TXT" to keep a [m:ss] marker on each line, which makes it easy to find the moment again.
- SRT for captions. YouTube, Vimeo, Premiere Pro, Final Cut Pro, and DaVinci Resolve all import it. For short on-screen captions you can edit against the video, or burn into it, use the caption generator.
- VTT (WebVTT) for the HTML5
<track>element and most web video players.
Getting a better transcript
- Pick the language when the clip is short or starts with music; automatic detection only hears the first seconds.
- Use Whisper Small for interviews recorded in noisy places, strong accents or specialist vocabulary.
- Long silences are skipped on purpose. Whisper tends to invent a "Thank you." when it is given silence.
- If a format will not open, export the audio as MP3 or WAV from your editor and drop that in instead.
When the desktop app is the better tool
This page transcribes one file so you can read it. The usual next problem is different: you have hundreds of interviews, vlogs and b-roll clips, and you need the one where someone said a particular thing. Reading transcripts one by one does not scale.
The Reelary desktop app transcribes every video in your footage library in the background, on your own machine, and makes all of it searchable. Type what was said, even roughly or in another language, and it jumps to the clip and the second. The same search also finds shots by what is in the picture, and the results drop straight onto a timeline. Read more about searching what was said in your footage.
The desktop app transcribes every video you own and lets you search all of it for what was said. Reelary is free to download for Mac and Windows; indexing and search have no file limit.
Questions
Is this video to text converter really free?
Yes. There is no sign-up, no watermark and no per-minute charge, because the transcription runs on your own computer rather than on a paid server. Files up to 1 GB and 30 minutes are accepted.
Is my video uploaded?
No. The browser reads the audio track from the file on your device and the Whisper model runs inside this tab. The only download is the model itself, fetched once from Hugging Face and cached by the browser.
How accurate is it?
It uses OpenAI Whisper, the same open model many paid services run. Whisper Base is fast and good for clear speech; switch to Whisper Small for accents, background noise or technical vocabulary. Proper nouns and overlapping speakers are the usual weak spots, so skim the result before publishing it.
How do I convert MP4 to text?
Drop the MP4 into the box above. The tool extracts the audio, transcribes it in 30-second pieces and shows the text as it goes. When it finishes, copy the text or download it as TXT, or as SRT or VTT subtitles with timestamps.
Which languages are supported?
Whisper recognises 99 languages and detects the language automatically. Choosing the language yourself is slightly faster and avoids misdetection on short clips. The output is in the spoken language; this tool does not translate.
Why is it slow on my computer?
Speed depends on your hardware. In Chrome or Edge with WebGPU, the model runs on your graphics card and usually transcribes faster than real time. Without WebGPU it runs on the CPU, which can take about as long as the video itself. Close other heavy tabs and keep this tab in front.
Can I transcribe a YouTube video?
Not by URL. The tool works on files you have on your computer, such as your own recordings, exports from your camera or downloads you have the rights to.
More free tools
Published October 10, 2026 · Models we use