Free Polish transcription can be judged in a minute. Published tests of others put the large-v3 word error rate for Polish at 4.74, the model behind Potok. Send a short clip full of long words and look at diacritics and case endings, where Polish text most often breaks.
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
- Polish scores quoted here were produced by other people on their own recordings, so your voice and room are untested.
- Polish marks several letters with diacritics, and a missing mark can turn one word into another.
- Case endings change a word's last letters, so a near-miss is still a wrong word.
- Consonant clusters are a good stress test.
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 a clip with hard words. Look for a surname, a street name and a number with a case ending.
- Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message, an audio file or a video.
- Scan for diacritics. Check every letter that should carry a mark.
- Check the endings. Read each noun against the audio and confirm the final letters.
- Scale up. If the clip is fine, send the full file, up to 2 GB, and export TXT, DOCX or SRT.
| 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 |
|---|---|---|
| Overlooking a missing diacritic | The word looks nearly right but means something else. | Proofread marks letter by letter. |
| Testing only with slow dictation | Fast speech is the real challenge. | Add a clip at natural pace. |
| Ignoring names | Surnames are guessed more often than common words. | Keep a list of names to compare. |
| Stopping after one tool | A single result has nothing to be measured against. | Run the same clip through two tools and compare the lines that differ. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How good is Polish in published tests?
Published tests of others give a word error rate of 4.74 on large-v3.
Is that your own measurement?
No. It comes from published tests of others.
Do I need to mark the language?
No setting is required. You send the clip and the bot works out the language from the speech itself.
Can I get the text in English?
No. The transcript stays in the language of the recording.
Is speaker labelling available?
Yes, it can be switched on, and speakers appear as numbers such as Speaker 1, not as real names.
What if the file is long?
Files up to 2 GB are accepted, and a long result comes as a file.
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