Korean speech to text in Potok is marked as recommended with a caveat: the published large-v3 word error rate is 14.1, close to the 15 line we use. It also depends on how spaces are counted. These are other people's tests, not our measurements. Send a short clip first.
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
- Because the figure sits near our cut-off, treat Korean as a language to proofread, not one to publish unseen.
- Word error rate counts space-separated words, and spacing in Korean writing is not always fixed, so the same speech can score differently.
- Politeness level changes verb endings, so a formal and a casual recording of the same idea produce different text.
- Numbers may appear as digits or as written words; decide which you want before editing.
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
- Start with a short test clip. Send one or two minutes first. It shows how your speaker, microphone and topic behave before you commit a long file.
- Find the bot. In Telegram open @potok_now_bot. Voice messages, audio files, video and YouTube links are all accepted.
- Send the long file. Up to 2 GB is allowed, and the Upload button in the mini app handles the biggest files.
- Check spacing first. Read a paragraph and look at where word breaks fall; this is where scores and human judgement differ most.
- Check endings and numbers. Make sure the formal or casual style matches the speaker and that numbers follow one style.
- Export. Choose TXT, MD, DOCX, PDF, SRT or VTT. Short transcripts show in the chat, long ones come as a file.
| 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 |
|---|---|---|
| Treating 14.1 as comfortably good | It is near the 15 line, and different counting of spaces would move it. | Plan a full read-through of every transcript. |
| Comparing two tools by spacing alone | Spacing choices can change a score without changing meaning. | Compare the content of sentences, not the break points. |
| Mixing formal and casual speech in one clip | Verb endings vary inside the transcript. | Split recordings by situation if the register matters. |
| Expecting person names for speakers | Labels are Speaker 1, Speaker 2 and so on. | Rename them after export. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is Korean recommended?
It is marked as recommended, but the published word error rate of 14.1 is borderline, so treat output as a draft.
Why does counting spaces matter?
Word error rate counts words, and where Korean text puts spaces is not always uniform, so the score can shift.
Whose figure is 14.1?
It is a published result for the large-v3 model from other people, not a measurement of ours.
Can the transcript be changed into another language?
No. The text is written in the language spoken in the recording.
How large can the file be?
Up to 2 GB, and the Upload button in the bot's mini app is meant for big files.
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
- Whisper speech recognition system (Wikipedia), Wikipedia · 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