Catalan speech to text in Potok is marked as recommended. The only figure we found comes from the earlier large-v2 model: a word error rate of 7.3, published by others and not measured by us. Send a voice message, audio or video to the Telegram bot and the text returns in Catalan.
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
- No large-v3 result for Catalan turned up, so the 7.3 describes an older model.
- Catalan has regional varieties, including Valencian, so an accent you know well is a fair thing to test.
- The score is a word error rate, meaning the share of words that differ from a reference.
- Video meetings and phone recordings both work as input.
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
- Choose the file. A meeting, a class or a family message are all fine. Note the speaker's region so you can judge the output fairly.
- Open the chat. Go to @potok_now_bot in Telegram and send the file or a link.
- Wait. Short results show up in the chat, long ones arrive as a file.
- Spot-check. Compare two or three paragraphs against the audio, paying attention to place names.
- Download. Pick TXT, DOCX, PDF, MD, SRT or VTT. Files up to 2 GB can be sent through Upload.
| 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 every regional variety scores the same | The 7.3 is a single figure and says nothing about a given accent. | Test a clip from your own speaker. |
| Calling it our result | The figure comes from a published study of an older model. | Describe it as published by others. |
| Sending a noisy street recording | Background sound lifts the error count. | Use a closer microphone where possible. |
| Cutting a long lecture by hand | You lose context and timestamps. | Send it whole; the limit is 2 GB. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why is the figure from an older model?
No large-v3 result for Catalan was found, so the large-v2 number is the one we can cite.
Is Catalan recommended?
Yes, it falls in the group of languages with good published results.
Does it understand Valencian?
The tests we found do not say, so try a sample of that speech before a long file.
Can I get timestamps?
Yes. Switch on timestamps and export SRT or VTT for subtitles.
Is the text in Spanish or English?
No. It stays in Catalan because the bot does not translate.
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