Transcribe audio to text
Upload an audio or video file and the transcript comes back with a timestamp on every segment, speaker labels on request and six export formats — nothing to install and no link to paste. The free plan is $0 with 3 files a day, and Pro is $10 a month when you pay yearly ($120 a year) or $20 a month when you pay monthly.
What you get, in numbers
Everything in this table is a number we can defend: it comes from the service contract, from the pricing page, or from a measurement we ran ourselves.
| What | Value | Where it comes from |
|---|---|---|
| Cheapest plan | Free — $0, 3 files a day, up to 30 minutes per file, no card | Pricing page |
| Pro | $10 per month billed yearly ($120 a year), or $20 per month billed monthly | Pricing page |
| Fair use on Pro | 1,500 minutes of audio per calendar month | Pricing page |
| One file | up to 64 MB and 120 minutes (two hours) — the same on every plan | Service contract |
| What comes back | text plus a start and end time for every segment; speaker labels on request | Service contract |
| Export formats | 6 — TXT, Markdown, SRT, VTT, CSV, DOCX (DOCX is a Pro feature) | Pricing page |
| Languages | Russian and English, set by you or detected automatically | Service contract |
| Speed | 0.84 s to transcribe a short file, 0.39 s to detect its language | our own measurement |
| API and agents | REST API v1, an MCP server with 4 tools, plugins for Claude and ChatGPT | Service contract |
| Accuracy | we publish no single accuracy number — ask for the evaluation report and the sample set | — |
How to transcribe audio to text
-
Upload the file
Drop an audio or video file on the widget, or send it from your own code with
POST /v1/transcriptsand a multipartfilefield. One file, up to 64 MB and 120 minutes. -
Set the language, or let the service detect it
Choose Russian or English in the widget, or leave it on automatic detection — 0.39 s on a short file in our own measurement. The API takes the same choice in the
languagefield:ru,enorauto. -
Ask for speaker separation
Switch on “Split by speaker” and the people in the room are told apart, so a two-hour conversation stays readable. The API takes the same switch in the
diarizefield. -
Read it, fix a word, export it
Every segment carries its start and end time. Correct a name in the editor, save, and export to TXT, Markdown, SRT, VTT, CSV or DOCX — the API reads the same transcript back, line by line, timecodes intact.
What a finished transcript looks like
One line per segment, with the time it starts and ends and the speaker it belongs to. The export files carry the same structure.
| Time | Speaker | Text |
|---|---|---|
| 00:04 | Speaker 1 | Мы перенесли релиз на четверг, потому что QA ещё закрывает два бага. |
| 00:11 | Speaker 2 | Okay, but the API rate limit is still 60 requests per minute. |
| 00:18 | Speaker 1 | Понял. Я подниму лимит до 300 и напишу в Slack. |
What it costs for your workload
The table below is calculated from the two published numbers — 1,500 minutes a month on Pro and $10 a month paid yearly — not measured per customer.
| Your workload | Minutes a month | Where it lands |
|---|---|---|
| 4 meetings of 45 minutes | 180 | 12% of the Pro allowance (calculated) |
| 25 one-hour lectures | 1,500 | exactly the Pro allowance (calculated) |
| 3 voice memos a day, 3 minutes each | 270 | 18% of the Pro allowance (calculated) |
| one two-hour interview | 120 | 8% of the Pro allowance; the Free plan refuses a file longer than 30 minutes |
Free and Pro, side by side
| Free — $0 | Pro — $10 per month paid yearly | |
|---|---|---|
| Files per day | 3 | no daily file limit |
| Length of one file | up to 30 minutes | up to 120 minutes |
| Minutes per month | up to 90 a day (3 × 30) | 1,500 fair use |
| Speaker labels | yes | yes |
| Export formats | TXT, Markdown, SRT, VTT, CSV | all six, DOCX included |
| API keys and MCP | no | yes |
| Card required | no | yes, via Stripe |
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.
How long does it take to transcribe an audio file?
On a short file our own measurement was 0.84 s for the transcription and 0.39 s for the language detection. Longer recordings take longer: our engine processes audio in 22-second fragments with a 3-second overlap, so a two-hour file is a few hundred fragments. The widget shows the status while it works, and we do not promise a fixed speed on a busy queue.
Which file formats can I upload?
Audio and video containers: mp3, wav, m4a, mp4, webm, ogg, flac, aac, wma, mov. One file at a time, up to 64 MB and 120 minutes.
Can I get the transcript as subtitles?
Yes. SRT and VTT are two of the six export formats, and the start and end time of every segment is written into them, so the subtitles line up with the audio.
Is there a free plan, and do I need a card?
Free is $0 with 3 files a day and up to 30 minutes per file, with timestamps, speaker labels and five export formats. No card, no trial clock. Pro is $10 a month when you pay yearly ($120 a year) or $20 a month when you pay monthly.
How accurate is it?
We do not publish a single accuracy percentage on this site. Our engine runs a model profile tuned for Russian speech, and we will send the evaluation report and the sample set on request — a score without its test set means nothing.
Can I paste a link instead of a file?
For YouTube links, no: the service takes files. Download the audio and upload the file — there is a step-by-step guide on the page how to transcribe a YouTube video.
Related pages.
Transcribe Russian audio to text
What our own engine does with Russian and with mixed Russian-English speech.
A checklist for calls, with speakers, timecodes and exports.
How to transcribe a long recording
The 64 MB and 120-minute limits, and how to split around them.
Every plan, every limit, in one table.
An honest comparison, including where we are worse.
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.