Potok transcribes Japanese audio and video in Telegram. Because Japanese is written without spaces, quality is a character error rate, and published tests of the large-v3 model report 4.5, a good result. You can send voice messages, recordings and 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 4.5 is a character error rate from a published large-v3 test, not a measurement we made.
- Japanese is written without spaces, so a character rate is used instead of a word rate.
- Text mixes kanji, hiragana and katakana, and the same sound can be written in several ways.
- Names are the weak point, since one spoken name may have several possible kanji.
What a transcript looks like
[00:00] Speaker 1: 会議を始めましょう。まず先週の結果を確認し、そのあと次のステップを計画します。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 |
|---|---|---|---|
| Japanese (日本語) | Recommended | character error rate 4.5% (large-v3, FLEURS) Whale paper | Published tests show a low error rate for this language. Japanese is written without spaces, so quality is reported as a character error rate, not a word error rate. |
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
- Share the clip. Send the Japanese recording to @potok_now_bot as audio, video, a voice message or a YouTube link.
- Upload if it is huge. Files up to 2 GB work; use the Upload button of the mini app for a long show.
- Use timestamps. With no spaces, long lines are hard to scan, so times help you navigate.
- Check names. Confirm the kanji of people and places against a reliable source.
- Check script choices. See whether words come out in kanji or kana where your style guide wants one.
- Export. Use SRT or VTT for subtitles, or TXT, MD, DOCX and PDF for text.
| 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 |
|---|---|---|
| Comparing 4.5 with a word error rate | The units differ, so the comparison is unfair. | Compare character rates with character rates. |
| Accepting a name in the wrong kanji | The person is misnamed in the document. | Check with the source. |
| Cutting subtitle lines mechanically | Line breaks fall in the middle of a word. | Edit the breaks in the SRT. |
| Waiting for an English version | The bot does not translate. | Translate separately. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How accurate is Japanese transcription?
Published large-v3 tests report a character error rate of 4.5 for Japanese. This is a figure from other groups.
Why not a word error rate?
Japanese has no spaces between words, so counting characters is the simpler and fairer measure.
Does it write kanji and kana?
Yes, the text mixes the scripts as normal Japanese does, though some choices may need editing.
Can I make subtitles?
Yes. Export SRT or VTT, then fix line breaks and names.
Is the text translated?
No. The transcript stays in Japanese, and the bot does not translate it into 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.
- Japanese writing system (Wikipedia), Wikipedia · checked
- Word error rate (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