To convert Hungarian audio to text, send it to the Potok bot on Telegram, knowing the language is borderline. Published tests of others on large-v3, not our measurements, report a word error rate of 14.11, close to the 15 line we use. Files up to 2 GB are accepted.
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
- Borderline here means the score sits just under our cut-off, so a small difference could move it over.
- Hungarian words carry many suffixes, so one wrong ending marks a whole word wrong.
- Test a short sample from your own speaker before a long upload.
- The transcript stays in Hungarian.
- The 15 line is our own cut-off for the good group, so a value just under it needs a sample check, not a promise.
What a transcript looks like
[00:00] Speaker 1: Kezdjük el az értekezletet. Először átnézzük a múlt heti eredményeket, aztán megtervezzük a következő lépéseket.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 |
|---|---|---|---|
| Hungarian (Magyar) | Recommended, borderline | word error rate 14.11% (large-v3, FLEURS) Canary-1B-v2 paper | Published tests show an error rate close to our 15% line. Check a short sample first. This figure is close to the 15% line we use, so treat it as borderline. |
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
- Test a sample. Because the score is near the line, send thirty seconds first.
- Open the bot. Open @potok_now_bot in Telegram.
- Send the full file. Up to 2 GB. Use the Upload button for big files.
- Check word endings. Compare suffixes with the audio, since a changed ending alters the meaning.
- Read the sample closely. Compare thirty seconds with the audio. If endings and names are mostly right, send the rest; if not, plan a heavy edit.
- Keep the original file. Hold on to the recording until you finish proofreading, so you can listen again to any doubtful passage.
- Export. DOCX or TXT for editing, SRT or VTT for 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 |
|---|---|---|
| Skipping the sample | A borderline language may suit one voice and not another. | Test first. |
| Ignoring endings | A wrong suffix changes the sense. | Check them. |
| Skipping the review | Errors are likelier than in the best languages. | Proofread. |
| Treating 14.11 as exact | It is an average from tests of others. | Judge by your recording. |
| Sending a long file after a bad sample | A poor first result suggests the whole file will need heavy editing. | Improve the audio or plan the extra proofreading first. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why is Hungarian called borderline?
Its published word error rate of 14.11 is close to the 15 line we use for the good group.
Which model is the figure from?
It comes from the large-v3 model, in published tests by other people, not from us.
What is the size limit?
The file limit is 2 GB per file, and the Upload button of the mini app handles large ones.
Is the text translated?
No. The text stays in Hungarian, the language of the recording you sent to the bot.
Can I send a video?
Yes, a video is read like audio, within the 2 GB limit of the bot.
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