Home › Video › Video to Text

Video to Text Converter

Transcribe the speech in a video to text on your device with Whisper: MP4, MOV, WebM, MKV in, plain text plus SRT and VTT subtitles out. 90+ languages, no upload, no account.

Drop files here, paste with Ctrl+V, or

Accepts .mp4, .mov, .webm, .mkv, .avi, .m4v, .mp3, .wav, .m4a · Processed on your device, never uploaded

Downloaded once from huggingface.co and cached: 40 to 250 MB on the CPU, 115 to 285 MB when the graphics card can run it (WebGPU).

Runs on Whisper in ONNX Runtime, on the graphics card when WebGPU is available. Your file stays in this tab.

About this tool

Get the words out of a video: a lecture recording, an interview, a screen capture with narration, or a clip that needs captions. The audio track is read straight from the file (or extracted by ffmpeg for containers the browser cannot open), then Whisper transcribes it on your device and returns plain text and timed SRT and VTT subtitles you can load into a video player, upload to YouTube, or edit with the subtitle tools here.

Nothing is uploaded, so long or private recordings are fine; the only download is the model, once. Pick Tiny for quick English drafts, Base for other languages or translation into English, Small for the most accurate captions.

How to use it

  1. Drop your MP4, MOV, WebM or MKV files into the box above, or click to browse. Nothing is uploaded.
  2. Adjust the options if you want; the defaults suit most files.
  3. Click the button and wait a moment.
  4. Download the results individually or all at once as a ZIP.

Questions

Can I burn the subtitles into the video?

Not here yet; download the SRT and load it in your player or editor, or upload it alongside the video on YouTube, which supports SRT and VTT captions.

How accurate is it?

Tiny is fine for clear English speech and gets names and jargon wrong; Base handles accents and other languages; Small is close to what paid services offer but takes several times longer. All run on your device, so a faster computer helps.

How long does it take?

In a browser with WebGPU (Chrome, Edge, and recent Safari on most computers) the model runs on the graphics card and an hour of audio takes a few minutes with Base. Without it, the CPU path transcribes Tiny about as fast as the audio plays, Base two to three times slower, and Small much slower: a one-hour recording with Tiny is a coffee break, with Small an afternoon.

Is the audio uploaded?

No. The model file is downloaded to your browser; the audio is decoded and transcribed on your device. The network panel shows only the model download.

Can I get subtitles?

Yes. Every transcript comes with SRT and VTT files with timestamps, ready for video players, YouTube, or the subtitle tools here.

Is it free, are files uploaded, which browsers work: the general questions are answered once for the whole site.

Format guides

Related tools

More video tools

View all
MOV to MP4.mov → .mp4MKV to MP4.mkv → .mp4WebM to MP4.webm → .mp4AVI to MP4.avi → .mp4MP4 to WebM.mp4 → .webmCompress VideoShrink MP4, MOV, WebM, and MKV videos for email, Discord, and messaging appsCompress Video for DiscordShrink a video to fit the Discord upload limit (10 MB free, 50 MB Nitro Basic, 500 MB Nitro) in your browserCompress Video for EmailMake a video small enough to attach to an email (25 MB Gmail and Outlook limit, or 20 and 10 MB) in your browser