MP3 to text
MP3 is the audio file every tool on the internet accepts, and Transcrib Si takes it as it is: 120 minutes per file. MP3 turns up in lectures, interviews, voice notes and podcasts, so there is nothing to convert and nothing to install — you upload the file and read the text.
What the service does with an MP3
Nothing about an MP3 is special to the engine. The file is uploaded, the speech inside it is written down, and the answer is a list of segments: every line carries the moment it starts and the moment it ends, so the text can be read next to the recording or turned into subtitles. The pipeline is the same one the general guide describes — the container is only a wrapper around the sound.
Two languages are recognized: Russian and English. You can set the language yourself or leave it on automatic detection, and the transcript states which of the two it used.
| What the file carries | The limit | Where it comes from |
|---|---|---|
| Size of one MP3 | 64 MB, the same on every plan | transcrib.si/pricing.html, checked |
| Length of one MP3 | 120 minutes on Pro and Team | transcrib.si/pricing.html, checked |
| Length of one MP3 on the free plan | up to 30 minutes; a longer file is refused with a clear error | transcrib.si/pricing.html, checked |
| How many files a day on the free plan | 3 | transcrib.si/pricing.html, checked |
| Audio a month on Pro | 1,500 minutes of fair use | transcrib.si/pricing.html, checked |
| Price of the free plan | $0, no card | transcrib.si/pricing.html, checked |
| Price of Pro | $10 a month paid yearly ($120 a year) or $20 a month paid monthly | transcrib.si/pricing.html, checked |
Where the numbers on this page come from
- 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
Why the format is not the hard part
MP3 is on the list of containers the upload picker accepts, together with nine others. Whatever the extension, the service reads the sound the same way and returns the same structure of segments and speakers.
| Container | What it usually holds | Accepted by the picker |
|---|---|---|
| mp3 | compressed audio | yes, named in the accept list of the upload field |
| wav | uncompressed audio | yes, named in the accept list of the upload field |
| m4a | compressed audio | yes, named in the accept list of the upload field |
| flac | lossless audio | yes, named in the accept list of the upload field |
| aac | compressed audio | yes, named in the accept list of the upload field |
| wma | compressed audio | yes, named in the accept list of the upload field |
| ogg | compressed audio | yes, named in the accept list of the upload field |
| mp4 | a video file with sound | yes, named in the accept list of the upload field |
| webm | a video file with sound | yes, named in the accept list of the upload field |
| mov | a video file with sound | yes, named in the accept list of the upload field |
The list is taken from the accept attribute of the upload field of the site itself: audio or video, and then the ten extensions mp3, wav, m4a, mp4, webm, ogg, flac, aac, wma and mov. Every page of this site, including the FLAC page and the AAC page, uses the same field.
Where the file is read
An MP3 in Russian, or in the Russian-English mix, is processed on our own transcription infrastructure, which sits outside the United States. A file that is entirely in English can be passed to a third-party cloud speech provider in the United States when that fallback is switched on for the server. The audio is used to produce the transcript and to run the service; it is never sold and never used to train models for other customers. On the free plan transcripts are kept for 7 days, and a deleted file leaves the live system at once and the encrypted backups within 30 days. The details are on the privacy page and in the security notes.
If the MP3 refuses to upload
- Over 64 MB. Split the recording, or compress it to a smaller MP3 — the limit is on the size of the file, not on the length of the sound.
- Longer than 30 minutes on the free plan. The free plan refuses it with a clear error. Pro takes files up to 120 minutes.
- A truncated file. If the recording was cut while it was being written, the end of the sound is missing and no service can recover it. Re-record or trim it in any editor first.
- Silence in a long file. A recording with long gaps is transcribed faster, not slower; the length of the file is what the 64 MB rule counts.
What you get back
The transcript, the segments with their start and end times, the speaker labels when you ask for them, and the export in the format you need: TXT, Markdown, SRT, VTT and CSV on every plan, DOCX on Pro. The exports are the same for every container, so an MP3 and a MOV of the same meeting give the same text. If you want the whole workflow, the guide to long recordings explains how to split a big file, and the meeting guide covers the speaker part.
Put a file on the page and read the first lines.
The widget below is the same one as on the home page: file → transcript with timecodes and speakers → export. The transcript is saved to your account.
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.
No account yet? The free plan needs no card. Create a free account or sign in.
Questions this page answers.
Which formats does the service accept besides MP3?
The upload field names ten containers: mp3, wav, m4a, mp4, webm, ogg, flac, aac, wma and mov. The picker also takes any file the system reports as audio or video.
How long can an MP3 be?
Up to 120 minutes and 64 MB per file on Pro and Team. The free plan accepts files up to 30 minutes and 3 files a day.
Does an MP3 keep the timecodes?
Yes. Every segment comes back with the second it starts and the second it ends, so the text can be lined up against the recording or exported as subtitles.
Can the speakers be separated?
Yes, on every plan. Tick “Split by speaker” before the upload and each line is marked with the voice it belongs to.
What happens to the MP3 after the transcription?
The audio and the transcript stay in your account until you delete them. A deleted file leaves the live system immediately and the encrypted backups within 30 days.
Related pages.
The lossless container, read the same way.
A Windows recording, uploaded as it is.
The sound of a video file, with the picture left out.
The general guide to the whole service.
Short recordings from a phone.
The plans and every limit.
Mark Burmistrov, Founder.
Every number on this page comes from the service contract, the pricing page or our own measurements. The author of the page and the publisher of the site are the same person. Questions and corrections: support@transcrib.si.