Upload the recording or paste a link. The interview comes back in Japanese script — what was said, in the language it was said in — with each turn marked in the transcript view and every word timed. Files over 500 MB continue on the upload page. A pack from $4 opens the full transcript · packs from $4 for 500 minutes.
How it works
Interviews, expert calls and long conversations.
The box above takes files up to 500 MB. A long interview continues on the upload page, which allows 10 hours or 5 GB per file.
Numbered speaker labels mark each turn in the transcript view, which matters in a language where a listener speaks constantly without taking the floor.
Click a word to hear it again. Export TXT, DOCX, SRT, VTT, MD or JSON when the text is right.
What Japanese interviews do
Japanese conversation has habits that shape how a transcript looks.
Japanese listeners say はい and ええ while the other person is still talking. Those land as their own brief turns, which is accurate but makes the page look busier than the conversation felt.
Keigo and humble forms are written as spoken, so the level of formality in the interview survives into the text rather than being flattened.
A spoken name can be written with more than one plausible set of kanji. Check personal and company names against your notes before a quote is published.
The transcript comes back written in Japanese. It is the language that was spoken, set down — not an English rendering of it.
What you get back
Research, reporting and internal expert calls.
The numbered labels live in the transcript view. TXT, DOCX, SRT and VTT download as words alone, and JSON is the export that records who said each segment.
Packs from $4, credits never expire and readable in full, at any length, which covers a long interview without a pack.
The text is searchable, so a term that came up once in a two-hour conversation is a search away rather than a re-listen.
Click any point and hear it. Checking a quote against the recording is the cheapest accuracy there is.
Pricing
A pack from $4 opens the full transcript. After that, one-time packs: $8 for 1,000 minutes, $12 for 2,000 minutes and $24 for 5,000 minutes. Credits never expire.
Twelve interviews of an hour come to 720 minutes, inside the $8 pack of 1,000 — about $0.58 an interview.
FAQ
Yes, written in Japanese script rather than romaji. It is not turned into English — Japanese audio produces Japanese text, and that is the file you download.
In the transcript view each turn carries a numbered speaker label. That is especially useful in Japanese, where short listener responses arrive constantly.
No. TXT, DOCX, SRT and VTT contain the words without labels. JSON is the one export that records which speaker said each segment.
Those are backchannels — はい, ええ, なるほど — said by the listener while the other person keeps talking. They are part of the recording, and you can read past them.
A name can often be written several ways, so check names against your own notes before publishing. The rest of the text is not affected by that ambiguity.
Up to 10 hours or 5 GB per file. The box here takes 500 MB, and larger recordings continue on the upload page.
That stretch comes back as English and the Japanese stretches come back as Japanese. The transcript follows the speaker; nothing is translated.
Instant preview, no signup. A pack from $4 opens the full transcript.