You can convert Korean audio to text by sending it to the Potok bot on Telegram, with one caveat. Published tests of others on large-v3, not our measurements, report a word error rate of 14.1, close to the 15 line we use, so treat Korean as borderline. 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
- The value 14.1 sits just under our 15 line, so a different test set could land on either side.
- Korean uses spaces between word groups, but the rules are flexible, so spacing alone can inflate the error count.
- Hangul is built from syllable blocks, so one wrong sound changes the whole block.
- Polite and plain verb endings differ, and the transcript keeps whichever the speaker used.
- Loanwords from English are written in Hangul, so product names may need a manual spelling pass.
What a transcript looks like
[00:00] Speaker 1: 회의를 시작하겠습니다. 먼저 지난주 결과를 검토하고, 그다음 다음 단계를 계획하겠습니다.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 |
|---|---|---|---|
| Korean (한국어) | Recommended, borderline | word error rate 14.1% (large-v3, FLEURS) Whale 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, and it depends on how spaces are counted, 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 thirty seconds. Because the score is borderline, send a short clip first and judge it before committing a whole interview.
- Open the bot. Go to @potok_now_bot in Telegram and send the sample.
- Send the full file. Up to 2 GB. For anything too big for a chat attachment, use Upload in the mini app.
- Compare spacing and endings. Check where spaces fall and whether verb endings match the level of politeness you heard.
- Enable labels for conversations. Numbered speaker labels help in a panel or an interview with turns that overlap.
- Export. DOCX or TXT to edit, 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 can hide problems until the end. | Run a short clip before the long file. |
| Reading spacing differences as wrong words | Two correct spellings of the spacing look like an error. | Fix spacing in one editing pass. |
| Trusting numbers | Figures and units are easy to mishear. | Check them against the audio. |
| Expecting speaker names | The bot only numbers voices. | Rename Speaker 1 and Speaker 2 after export. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why is Korean marked borderline?
Its published word error rate of 14.1 is close to our 15 line, so results can swing between recordings.
Does spacing change the score?
Yes. Spacing rules are loose, so the way spaces are counted can move the figure.
Which model gave the 14.1?
Published tests of other people on the large-v3 model. We did not measure your audio.
What is the file size limit?
2 GB per file, with the Upload button for large ones.
Can I send a drama clip?
You can send video files you have the right to use. The speech is read from the sound track and written as Korean text.
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
- Whale paper, Table 5 (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