A Korean transcript from Potok is plain Korean text, one block per speaker, with optional timestamps. Published word error rate for large-v3 is 14.1, just under the 15 line we use, so treat Korean as borderline and plan a read-through. The bot takes files up to 2 GB.
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 14.1 is a word error rate from published tests of others, not our measurement, and it sits close to the 15 line.
- Spacing rules in Korean writing are not applied uniformly, so the count of words depends on where spaces are placed.
- Particles and endings attach directly to the preceding word, which makes word-level scoring harsher than it feels when reading.
- Speaker labels appear as Speaker 1, Speaker 2 and so on, never as real names.
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
- Open the bot. Open @potok_now_bot in Telegram and pick the chat where you want the text to arrive.
- Send the Korean recording. A voice message, audio file, video or YouTube link all work. Anything up to 2 GB goes through, and the Upload button of the mini app handles the largest files.
- Choose how the transcript is laid out. Switch on speaker labels for an interview, and timestamps if you plan to jump back to a line later.
- Skim for spacing. Read the first minutes and decide whether the word breaks suit your style before you export everything.
- Export. Save TXT or MD for notes, DOCX or PDF for sharing, and SRT or VTT for subtitle 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 14.1 as a safe margin | A small change in the audio or the test set can push the result past the line. | Keep a proofreading pass in the plan. |
| Fixing spacing in every line by hand | Hours go into a detail that rarely changes the meaning. | Correct names and numbers first and leave spacing for a final pass. |
| Expecting formal and casual speech to read alike | Endings differ with the speaker, so a mixed conversation looks uneven. | Check one speaker at a time. |
| Cutting subtitles at the exported line breaks | Lines may end in the middle of a phrase. | Adjust the breaks in the SRT file. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
What does a Korean transcript look like?
It is Korean text in blocks, each with a speaker label and, if you ask for them, a time before the line.
Why is Korean marked as borderline?
Published large-v3 results give a word error rate of 14.1, which is close to the 15 line, and word counts depend on spacing.
Can I get subtitles?
Yes. Export SRT or VTT, then check line breaks and names before you publish.
Does the bot name the speakers?
No. Labels are numbers such as Speaker 1, and you replace them with real names in your editor.
Will I get an English version?
No. The text stays in Korean, and the bot does not offer a version in another language.
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