Send your Catalan audio to the Potok bot on Telegram and the text comes back in the chat. Published tests of others on the earlier large-v2 model, not our measurements, show a word error rate of 7.3 for Catalan. No large-v3 figure was found. Files up to 2 GB work.
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
- Word error rate is the share of words that differ from a correct reference, so a lower number is better.
- No large-v3 figure for Catalan was found, so the number comes from an older model.
- A low rate is not a promise for noisy or overlapping speech.
- Short results arrive as chat text, long ones as a file.
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
- Gather the recordings. Put every Catalan clip in one folder and name them by date or speaker, so you can match the replies to the right files later.
- Open the bot. Open @potok_now_bot in Telegram.
- Attach each file. Send audio, a voice note, a video or a YouTube link. The limit is 2 GB per file, and the Upload button of the mini app helps with big ones.
- Wait for the reply. A short clip is answered in the chat as text. A long recording arrives as a file you can open or forward.
- Export what you need. TXT, MD, DOCX, PDF, SRT or VTT. Pick SRT if the text will become 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 |
|---|---|---|
| Reading the 7.3 as a large-v3 result | It comes from the earlier model, so it may not match the current one. | Say which model the figure belongs to. |
| Sending two voices that overlap | Overlapping speech confuses any recogniser. | Ask people to speak in turn, or turn speaker labels on. |
| Skipping names | Surnames and place names are the likeliest errors. | Check them against your own notes. |
| Sending a clip with background music | Music masks the voice. | Send a version without music if you have one. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is Catalan supported?
Yes. Its published word error rate of 7.3 is in the good range, although it comes from the earlier large-v2 model.
Why is the figure from an older model?
No large-v3 result for Catalan was found in the public sources we use.
How long can the recording be?
The file can be up to 2 GB. Use the Upload button for the largest files.
Can I get timestamps?
Yes, you can switch them on and export SRT or VTT for subtitles.
Will the text be in Spanish?
No. The transcript stays in the language of the recording.
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