Polish speech to text in Potok is a recommended language: published tests of the large-v3 model give a word error rate of 4.74. This is a result from other people's tests, not our measurement. Send a voice note, audio or video to the Telegram bot and read the output before sharing.
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
- About one word in twenty can differ from a human reference at 4.74, though real recordings are usually harder than test sets.
- Polish nouns and adjectives change their endings with case, so one wrong ending is the most common small slip to look for.
- Diacritic letters such as the ones with a tail or an acute mark can be dropped or swapped; scan words that carry them.
- Long consonant clusters in names and surnames are a typical spot for spelling mistakes.
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
- Choose the source. A webinar, a call recording or a dictated memo works. Keep the original file rather than a heavily compressed copy.
- Send it. Open @potok_now_bot and share the file; a forwarded voice message or YouTube link is fine too.
- Upload large ones. Files up to 2 GB are accepted, with the Upload button for the largest.
- Check endings. Scan a page for wrong case endings, which change meaning even when the word looks right.
- Check names. Surnames and place names with unusual clusters need a second look.
- Export. Pick TXT, MD, DOCX, PDF, SRT or VTT.
| 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 |
|---|---|---|
| Trusting the 4.74 figure on a noisy line | Test speech is cleaner than a call. | Treat the number as a best case. |
| Skipping the diacritics check | A missing mark can produce another valid word. | Search for common words that carry them and compare. |
| Not turning on speaker labels in a panel | Voices run together. | Switch labels on before sending. |
| Sending a phone call recorded far from the speaker | Distance adds echo. | Record closer to the voice. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How well does Polish score in tests?
We make no promise of our own; published tests of the large-v3 model show a word error rate of 4.74 for Polish.
Are these measurements yours?
No, they are published results from other people.
What mistakes are typical?
Case endings, diacritic letters and unusual names are the places to read most carefully.
Can I send a YouTube link?
Yes, YouTube links are accepted along with files and forwarded voice messages.
Does the bot change the Polish text into another language?
No. The transcript stays in Polish, exactly as spoken, and no other language version is produced from it.
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