Skip to the tool
Cutwisp
EN

Video to text

Cutwisp listens to the speech in your video and writes it down. The speech recognition runs in your browser, so the video never leaves your device.

How it works

  1. Open your video file.
  2. Choose the language spoken in the video. Use the yellow handles if you only want part of it.
  3. Click "Transcribe". The text appears below while Cutwisp works. Save it as TXT or as SRT subtitles.

Questions and answers

How accurate is the text?

With clear speech, most of the text is right. Music, noise, strong accents and several people talking at once lead to more mistakes. Read the text through before you use it.

How long does it take?

That depends on your device. The first time, your browser also loads the speech model. On a test laptop with an Intel Core i5 from 2022, Standard needed about 2 minutes for 3 minutes of speech. More accurate takes much longer, and phones are slower. Keep the browser tab open until it is done.

What is an SRT file?

A subtitle file with start and end times for each line. VLC, most video editors and YouTube can load it together with the video.

Which speech recognition does Cutwisp use?

Whisper, a speech recognition model that OpenAI released under the MIT license. Cutwisp runs it in your browser with the transformers.js library.

Is my file uploaded?

No. Cutwisp processes the file inside your browser. It is never sent to a server.

Does it cost anything? Is there a watermark?

Cutwisp is free, and it doesn't add a watermark.

Sound and audio