A Polish transcript from Potok keeps the diacritic letters and arrives in the chat as text or as a file. Published tests of the large-v3 model report a word error rate of 4.74, one of the lower figures we cite. Files up to 2 GB work, with six export formats.
Transcribe a recording
Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.
Open @potok_now_bot in Telegram
Files up to 2 GB · export to TXT, MD, DOCX, PDF, SRT and VTT · speaker labels and timestamps · about 30 languages
Key facts
- The 4.74 comes from published tests of others on large-v3, not from our own measurements.
- Polish adds nine letters with marks, such as the l with stroke and the z with dot, and a missing mark changes the word.
- Case endings change the end of a word depending on its role in the sentence.
- Timestamps and numbered speaker labels are switched on only when you ask.
What a transcript looks like
[00:00] Speaker 1: Zacznijmy spotkanie. Najpierw omówimy wyniki z zeszłego tygodnia, a potem zaplanujemy kolejne kroki.Meaning in English: Let's start the meeting. First, we'll review last week's results, then plan the next steps.
Written by us to show the script and the layout of a transcript. It is not the output of the recognition engine.
Published quality
| Language | Verdict | Published result | Notes |
|---|---|---|---|
| Polish (Polski) | Recommended | word error rate 4.74% (large-v3, FLEURS) Canary-1B-v2 paper | Published tests show a low error rate for this language. |
These numbers come from published tests by other people, not from tests by Potok. Your own audio, with its noise, accents and microphone, will differ.
How to do it
- Send the Polish file. In @potok_now_bot post a voice message, an audio or video file, or a YouTube link.
- Use Upload for the heavy ones. Recordings up to 2 GB are fine; the mini app's Upload button is meant for the largest.
- Enable labels for several voices. Each turn then starts with Speaker 1, Speaker 2 and so on.
- Open the DOCX or PDF on a screen. Confirm that every special letter shows correctly in your font.
- Search for look-alike words. Find words that differ only by a diacritic and verify the ones that matter.
- Export to captions if needed. SRT and VTT work for subtitles.
| Feature | Details |
|---|---|
| Where it works | Telegram bot @potok_now_bot; large files go through the bot's mini app |
| File size | Up to 2 GB |
| Export | TXT, MD, DOCX, PDF, SRT, VTT |
| Speakers and time | Speaker labels and timestamps can be switched on |
| Languages | About 30 languages with good published results; a few more with warnings |
| Translation | The transcript is not translated into another language |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Opening a TXT file in the wrong encoding | Special letters turn into odd symbols. | Open it as UTF-8 or use DOCX. |
| Ignoring ending differences in quoted names | A name may appear in a case form instead of its basic form. | Restore the basic form where a list or index needs it. |
| Calling 4.74 our accuracy | It is a published figure from other tests. | Cite it as large-v3 word error rate from others. |
| Expecting English output | The text is not translated. | Use a separate tool if you need another language. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Does the Polish transcript keep the special letters?
Yes, the text is normal Polish with diacritics, so check that your editor uses a font that shows them.
What is the published error rate?
A word error rate of 4.74 for large-v3, reported in tests by others.
How do I get timestamps?
Switch them on before sending the file. They then appear before each paragraph.
Can I export subtitles?
Yes, SRT and VTT are among the six formats.
What is the biggest file I can send?
Up to 2 GB, using the Upload button in the mini app for the biggest ones.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Word error rate (Wikipedia), Wikipedia · checked
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
- Canary-1B-v2 paper, Table 11 (Whisper large-v3 on FLEURS) · checked
Try it on your own recording
Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.
Open @potok_now_bot in Telegram