Transcribe the speech in a video and get a draft: an introduction, key points and a conclusion
Drop your file here or click to browse
Accepted: .mp4,.mov,.avi,.mkv
Your result will appear here once processing is complete.
This tool transcribes the speech in a video with Whisper, then arranges excerpts of the transcript under three headings: an introduction, key points and a conclusion. It is not a finished article. The tool does not reword or summarize anything, so treat the result as a starting point to read through and rewrite. For a video spoken in French, the headings come out in French.
Drag an MP4, MOV, AVI or MKV file into the tool, or click to pick it on your device.
Whisper turns the speech in your video into text.
Get a text file with an introduction, key points and a conclusion taken from the transcript.
Your original video is not changed. You get a text file.
No need to type out what is said in the video.
Your video is deleted from our servers within 30 minutes.
Everything runs in your browser, with no software or extension to add.
Computer, tablet or phone: a web browser is all you need.
Processed over HTTPS and automatically deleted from our servers within 30 minutes.
No watermark. A daily limit applies to free use.
The speech is transcribed by Whisper first. The introduction is the first 500 characters of the transcript. The key points are about five sentences taken at regular intervals through the video. The conclusion is the last sentence spoken.
Nothing is summarized or reworded: these are raw excerpts. The result depends on the sound (a clear voice, little noise) and on what is said. Plan to read it, fix proper names and rewrite. For the full transcript, see audio transcription.
A draft taken from a video is a starting point.
No. It transcribes the speech in your video with Whisper, then arranges excerpts of that transcript under three headings. Nothing is rewritten or reworded.
The introduction is the first 500 characters of the transcript. The key points are about five sentences taken at regular intervals through the video. The conclusion is the last sentence.
For a video spoken in French, the headings are in French (Introduction, Points clés, Conclusion). Otherwise they are in English.
The transcript depends on the quality of the sound: a clear voice, little noise, no loud music. Always read it through and fix mistakes, especially proper names.
No. The tool works on a file you upload, not on a link.
For the full transcript, use the audio transcription tool or the automatic subtitles.
Yes: 20 minutes at most. Longer files are refused. For a longer video, first pull out the sound with Extract Audio From Video, cut it with Extract Audio Clip (start time and length in seconds), then use the audio transcription tool.
Yes: Whisper detects the spoken language. Quality varies with the language, the accent and how clear the sound is.
MP4, MOV, AVI and MKV. The result is a text file.
Yes, it depends on your plan: no account, a free account, or a paid plan. The current limits are listed on the Pricing page.
Yes. The tool runs in your browser, so it works the same way on Windows, Mac, Android, and iPhone without installing anything.
Your file is processed over HTTPS and automatically deleted from our servers within 30 minutes.
File Tools Online offers free tools in your browser for video, audio, image and PDF files. The draft tool is part of its transcription tools.
Typing out a video by hand takes hours. Automatic speech recognition does most of the work, and you only have to read it through.