To test a free Hungarian transcription tool, send a short clip and look closely at word endings, because Hungarian is borderline. The published word error rate for large-v3 is 14.11, close to the 15 line Potok uses, and it is other people's number.
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 14.11 is a word error rate for large-v3 in a published test, not our measurement.
- This figure is close to the 15 line we use, so treat it as borderline.
- Hungarian attaches many endings to a word, so one wrong ending makes the whole word wrong.
- The transcript stays in Hungarian and is not translated.
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
- Pick endings-heavy speech. Choose a clip with sentences full of inflected words, such as a story told in the past.
- Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message or an audio file.
- Read the endings. Compare each ending with the audio. They carry meaning in Hungarian.
- Check name order and accents. Hungarian marks long vowels with accents. Look for dropped marks.
- Judge the borderline. If the clip needs many fixes, plan a full proofread of every file. Up to 2 GB is accepted, with Upload in the mini app for large files.
| 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 14.11 as comfortably good | It sits near the 15 line. | Plan on corrections. |
| Ignoring dropped accents | A missing mark changes the word. | Scan for plain vowels where marks belong. |
| Overlooking endings | The stem is right, the ending wrong. | Count these as errors. |
| Testing on poor audio first | It hides what the tool does with the language. | Begin with a clean sample. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why is Hungarian marked borderline?
Its published error rate is close to the 15 line we use.
What does 14.11 measure?
The word error rate for large-v3 in a published test by others.
Can I use timestamps for checking?
Yes, they let you jump to a doubtful phrase.
Which formats can I export?
You can save the transcript as TXT, MD, DOCX, PDF, SRT or VTT, which covers editing as well as subtitles.
Will the text be in English?
No. The transcript stays in the language of the recording.
What kind of clip works best?
A minute of relaxed storytelling works well, because it uses many inflected words and shows how the tool handles endings.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
- Word error rate (Wikipedia), Wikipedia · 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