MP4 to Text Converter
Drop in an MP4 video and get a free transcript and captions file. The audio track is read in your browser, so the video never uploads.
How to convert MP4 to text
- Drop your MP4 in the box above or choose it from your device. MOV and M4V files work in most browsers too.
- Choose Fast or Accurate.
- Press Transcribe. Your browser pulls out the audio track and transcribes it.
- Download .srt captions for your video editor or YouTube, or copy the plain text.
Want to know how long the transcript runs when you read it aloud? Paste it into the words to minutes calculator.
Turn any MP4 into a transcript
The MP4 stays on your computer. Your browser pulls the soundtrack out of the video and transcribes that audio locally. The video file is never uploaded, and the speech model downloads once from the Hugging Face hub.
Video files are big. Skipping the upload saves time on its own, and unreleased client work never leaves your laptop.
Make captions from your MP4
- YouTube Studio: open the video, go to Subtitles, add a language, then Upload file and choose With timing.
- Premiere Pro, DaVinci Resolve and Final Cut Pro all import .srt as a captions track.
- Read the captions once against the video. Fix names and break any line that runs too long on screen.
Put the captions back on the video
Download the .srt and drop it on the MP4 in your editor or in YouTube Studio. Paste the plain transcript into the words to minutes calculator to see how long the narration runs.
If a line is stiff, hear a new read in 100+ AI voices before you re-record that part of the video.
More free audio converters
MP4 to Text FAQ
Is my MP4 uploaded anywhere?
No. The browser reads the MP4 locally and transcribes the soundtrack. The video is not sent to Script Timer. The speech model downloads once from the Hugging Face model hub and your browser caches it.
Is an MP4 transcript free?
Yes. Captions and a transcript from an MP4 need no sign-up and add no watermark. One video can run up to 60 minutes.
What model transcribes the video's audio?
OpenAI's open-source Whisper model, run in the browser with transformers.js. Fast uses Whisper Tiny for a quick caption pass. Accurate uses Whisper Base when the soundtrack has noise or more than one speaker.
Why is the first video slower?
The first MP4 waits while the browser downloads the speech model. Later videos use the cached model. A large video can also take a moment to open on a phone, so a computer is the better place for long files.
Does it work with large video files?
Only the audio is processed, so a big video is fine as long as it runs 60 minutes or less. Very large files can be slow to read on a phone, so use a computer if you can.
Hear it before your audience does
Paste your script into Script Timer to time it, grade the delivery and hear it in 100+ AI voices.
In-browser speech recognition follows whisper-web (MIT license).