Potok can convert Japanese audio to text when you send the file to its Telegram bot. For Japanese, quality is reported as a character error rate, because the language has no spaces. Published tests of others on large-v3, not our measurements, give 4.5. 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
- Japanese quality is a character error rate, a count of wrong characters rather than wrong words.
- Text mixes kanji, hiragana and katakana, and the same sound can be written with several different characters.
- Because there are no spaces, a line break in the export may fall inside a phrase.
- Numbers and units can appear as digits or as characters, so check the style your document uses.
- Spoken fillers and trailing sentence endings are common in casual Japanese and may or may not appear in the text.
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
- Open the bot first. Start @potok_now_bot in Telegram so the chat is ready when the recording is.
- Send the recording. Attach audio or video, forward a voice message, or paste a YouTube link. Files up to 2 GB are accepted.
- Use the mini app for bulk. When a file is too big for a chat attachment, the Upload button in the mini app takes it.
- Wait for the reply. A short transcript arrives in the chat. A long one arrives as a file you can open and edit.
- Check homophones. Search for words that sound alike, such as names and technical terms, and compare the chosen characters with your source.
- Export. Pick DOCX or TXT for editing, SRT or VTT for captions.
| 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 |
|---|---|---|
| Looking for a word error rate | Japanese has no spaces, so that metric does not fit. | Read the published figure as a character error rate. |
| Trusting the choice of kanji for names | The sound is right but the characters may not be. | Check personal and place names against a written source. |
| Splitting lines by hand at spaces | There are none to split on. | Break lines at punctuation instead. |
| Mixing in a long English passage | Switching language mid-file confuses the output. | Cut the file where the language changes. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why is the figure a character error rate?
Japanese is written without spaces, so researchers count characters instead of words. The published value is 4.5 on large-v3.
Does the transcript include furigana?
No. You get ordinary Japanese text, and reading aids would need to be added by hand.
Can I send a long meeting recording?
Yes, up to 2 GB per file, using the Upload button if the chat will not take it.
Is the 4.5 measured by you?
No. It comes from published tests by other people, so treat it as a guide, not a promise.
Do I get timestamps?
You can switch them on before sending and export SRT or VTT for subtitles.
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