Potok handles Catalan audio and video in a Telegram chat and returns the text in Catalan. The published word error rate is 7.3, but it comes from the earlier large-v2 model because no large-v3 figure was found. Send voice notes, recordings or files up to 2 GB.
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 7.3 is a word error rate from published tests of the earlier large-v2 model, not from our own runs.
- We found no large-v3 result for Catalan, so the figure may not match the current model.
- Catalan uses accents and marks such as the grave and acute accents, the cedilla and the middle dot in words like col·legi.
- Speech that switches between Catalan and Spanish is not covered by the published figure.
What a transcript looks like
[00:00] Speaker 1: Comencem la reunió. Primer repassarem els resultats de la setmana passada i després planificarem els propers passos.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 |
|---|---|---|---|
| Catalan (Català) | Recommended | word error rate 7.3% (large-v2, FLEURS) Whisper paper | Published tests show a low error rate for this language. No large-v3 figure was found; the figure is from the earlier large-v2 model. |
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
- Open the chat. Go to @potok_now_bot and send your Catalan recording as a voice message, file or YouTube link.
- Large file? Upload it. Up to 2 GB is accepted. Use the mini app's Upload button when a plain chat attachment is too heavy.
- Read for language switches. If speakers jump to Spanish mid-sentence, check those lines by hand because the figure says nothing about mixed speech.
- Check accent marks. A wrong accent can change a word, so scan the text for it before sending it on.
- Export. Pick TXT, MD, DOCX, PDF, SRT or VTT depending on whether you need notes, a document or 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 |
|---|---|---|
| Assuming the old-model figure describes the current one | The real error rate on your audio could be higher or lower. | Test a short clip from your own speakers. |
| Ignoring bilingual passages | Spanish words inside Catalan speech may be written wrongly. | Review the places where the language changes. |
| Dropping the middle dot in words like col·legi | A search for the correct spelling finds nothing. | Fix the spelling in your editor and keep the dot. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Which model does the Catalan figure come from?
From published tests of the earlier large-v2 model. We found no large-v3 figure for Catalan, so the note on this page stays.
Is Catalan a recommended language here?
Yes, the published word error rate of 7.3 puts it among the good results on our list, with the model caveat above.
Does it work for Valencian or Balearic speech?
The published figure does not separate regional varieties, so test a short sample from your speaker before a long recording.
Can I add timestamps to the Catalan text?
Yes. Speaker labels and timestamps can be switched on, and the labels appear as numbers rather than names.
Does the bot translate Catalan to Spanish?
No. The transcript stays in Catalan, and translation is not offered.
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
- Whisper paper, Table 13 (large-v2 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