MP4 to text
MP4 is the container every camera and phone writes, and Transcrib Si reads the sound track out of it: 120 minutes per file. It holds a picture and sound, and for most people the picture is a by-product of the recording. The reason to transcribe an interview or a lecture is the speech.
What happens to the picture: nothing. The service reads the sound and ignores the frames. .mp4 is on the accepted list, the same 64 MB and 120-minute limits apply to every plan, and the transcript comes back with a timestamp on every line.
Audio inside a video file
An MP4 file is a set of tracks in a box: one for the video, one for the sound, sometimes more than one of each. The sound is usually AAC, the video is usually H.264, and both are compressed, which is why a one-hour MP4 can sit comfortably in a hundred megabytes and still hold a full hour of talk.
That compression is also why a video recording often fits the upload limit while the same speech saved as WAV would not. If you want to know exactly what the file holds, any media player will show you the track list. If you want to know how big it is, your file manager will do that faster.
| Track | Usual codec | What the service does |
|---|---|---|
| Video | H.264 | Ignored |
| Audio | AAC | Transcribed, timestamped, split by speaker |
| Extra audio | Any | Accepted as one recording |
| Subtitle track | Text | Left alone — the text is generated from the sound |
From camera to transcript
The same routine that works for a voice memo works for a video.
-
Move the file to the machine with the browser
Watch, AirDrop, a card reader, a messenger, a cloud folder — any of them will do. The file stays an .mp4, and the extension is what the uploader recognises.
-
Send it, and say what you want
Automatic language detection is fine for most files. If two people are speaking, turn on the speaker split so the transcript keeps the conversation readable.
-
Take the text and, if needed, the subtitles
Export SRT or VTT to caption the video itself, or TXT, Markdown, CSV or DOCX to send the words to someone else. One recording, several outputs, no second upload.
Drop an audio or video file
or — mp3, wav, m4a, mp4, up to 64 MB and two hours
Transcription runs under your account: sign in or create a free account.
The free plan asks for no card. Create a free account or sign in.
The price of one MP4 file
Charged by the length of the sound, not by the length of the film. Thirty minutes of speech inside a two-hour video costs the same as thirty minutes on its own.
| Plan | Price | Allowance | Per-file limit |
|---|---|---|---|
| Free | $0 | 3 files a day, 30 minutes per file | 64 MB |
| Pro, billed yearly | $10 per month, $120 for the year | 1,500 minutes of audio per calendar month | 64 MB and 120 minutes |
| Pro, billed monthly | $20 per month | 1,500 minutes of audio per calendar month | 64 MB and 120 minutes |
Video files eat the 64 MB allowance quickly, so an MP4 recorded at a high resolution can hit the wall even when the speech is short. Sending the sound track on its own is the usual fix; the long recording guide explains how to split a file that is too big either way.
Questions this page answers.
Will the transcript mention what is on screen?
No. What you get is the spoken content only: the words, the order, the timings. If you also need a description of the visuals, that is a different kind of work and a different tool.
Is it better to send an MP4 or to extract the audio first?
Both give the same transcript. Sending the MP4 is one step fewer; extracting the audio is smaller on the wire and sidesteps the 64 MB ceiling on a long, high-resolution recording. Either way, the words do not change.
Can the transcript become subtitles for my video?
Export the result as SRT or VTT and drop the file next to the video. The subtitle timings come from the same timestamps as the transcript, so the captions land on the right seconds.
Does the length of the video count against my allowance?
Only the audio does. The free plan counts 3 files a day with up to 30 minutes of sound each; Pro counts 1,500 minutes of audio per calendar month. A silent video costs you nothing beyond the upload.
Which other formats can I send?
mp3, wav, m4a, mp4, webm, ogg, flac, aac, wma and mov. The general guide has one section per container, and the WebM page covers the other video container in detail.
Where the numbers on this page come from
Each line names the page the figure was read on and the day it was read.
- Free $0, 3 files a day, 30 minutes per file, 64 MB — https://transcrib.si/pricing.html — checked 2026-10-25
- Pro $10 per month ($120 for the year), $20 per month, 1,500 minutes per calendar month, 120 minutes per file — https://transcrib.si/pricing.html — checked 2026-10-25
- Accepted containers: mp3, wav, m4a, mp4, webm, ogg, flac, aac, wma, mov — https://transcrib.si/app.html (the file input of the upload form) — checked 2026-10-25
- Exports in TXT, Markdown, SRT, VTT, CSV and DOCX — https://transcrib.si/pricing.html — checked 2026-10-25
Where to go next
WebM to text
The other video container, and why its files are so heavy.
M4A to text
The audio-only cousin of the MP4 file.
What an hour of audio costs
The price per minute at a dozen services, checked on one day.
Transcribe audio to text
The general guide to every container and export.
Plans and prices
Every plan, every limit, no fine print.
Security
How the file is handled while it is being read.
More to read: the privacy policy, the terms of service, about the author, the contact page and the app.
Mark Burmistrov, Founder.
Every number on this page comes from the pricing page, the service contract or the upload form itself. The author of the page and the publisher of the site are the same person. Questions and corrections: support@transcrib.si.