Skip to content
Try it free

MP4 to Text Converter

Only the audio leaves your browser. Up to 100 MB and about 50 minutes here. For a longer video, save the audio first.

Free to try, no sign-up. Nothing leaves your browser until you press the button.

How it works

  1. Drop the video

    MP4, MOV, M4V, WebM or MKV, up to 100 MB and about 50 minutes of audio.

  2. The audio is read locally

    You see Reading audio, then Uploading audio. The video stays on your computer.

  3. Get the transcript

    Read it with timestamps, copy it, or export SRT, VTT, TXT or Markdown.

A narrated screen recording

Sample
  1. 0:00

    I am going to show you how to set up the export preset.

  2. 0:05

    Open the Export panel and choose Custom from the preset list.

  3. 0:12

    Set the frame rate to match your source, 30 in this clip.

  4. 0:19

    Then save the preset, and it shows up in every project.

Illustrative sample from a narrated screen recording. A tutorial becomes a written walkthrough.

What leaves your browser

Your browser pulls the audio track out of the MP4 and uploads that mono file. The video and its frames stay on your computer, whatever is on screen.

If the browser cannot read the audio, nothing is sent. The upload is deleted when the job succeeds. You can check what goes up in your browser network panel: it is one audio file named after your video, ending in .wav.

Containers

It comes down to whether your browser can decode the audio inside. A phone video is usually an MP4 or MOV with AAC audio, and both read fine. A QuickTime Player screen recording is an MOV.

ContainerIn the browser
MP4Works in most browsers when the audio is AAC.
MOVOften works, including Mac screen recordings.
WebMWorks in most browsers.
MKVThe least reliable. Convert it to MP4 first if the browser cannot read it.

Next steps

The transcript opens with timestamps and exports as SRT, VTT, TXT, Markdown and JSON. A narrated tutorial becomes a written walkthrough you can edit. Check it against the video before you quote it.

An hour-long MP4 can be small, but its audio becomes a WAV of about 1.9 MB a minute. That is why the page stops at about 50 minutes. Cut a longer video first, or save the audio as an MP3 or M4A.

To read the text on the screen as well, paste the video link on video to text and choose Both. For subtitles, see the SRT generator. The sources and limits page covers file size and length.

Limits

100 MB and about 50 minutes of audio per file in the browser. Listen only for files. Watch runs in the command-line tool (the Mac app is not out yet). Without an account: videos up to 15 minutes and 10 minutes a day.

See pricing · How minutes are counted · Paid plans are not on sale yet.

Questions

Drop the MP4 on the box above. When you press Get transcript, the browser reads the audio track and uploads only that.

Up to 100 MB in the browser, and about 50 minutes of audio from a video, because the browser sends the audio as a WAV. Past that, save the audio as an MP3 or M4A on your computer and upload that, or cut the video into parts.

No. The browser decodes the audio locally and sends a mono audio file. If it cannot read the audio, the upload is refused.

Not for files on the web, which are read for their audio only. Paste the video's link on the video to text page and choose Watch to read the screen.

Yes. The result page exports SRT, VTT, TXT, Markdown, Context and JSON, and has a Print / Save as PDF option.

Agents and code

Use it in your agentUse the API