How the video gets in
Drop in the video file unchanged: MP4, MOV, MKV, WEBM, AVI, M4V, 3GP or a phone screen recording. The sound track is pulled out on the server, so there is no convert-to-MP3 step, and every timestamp still matches the picture. If the video is online, paste its public link under Import from link: YouTube, Shorts, TikTok, public Vimeo, Dropbox or Google Drive share links, or a direct link to a video file. Only the audio is downloaded. Playlists and channels are refused, so queue videos one link at a time, and sign-in-only posts such as Instagram need to be downloaded and uploaded.
The transcript then plays in sync with the video: the current line is highlighted, and clicking a line jumps playback there so you can check a reading by ear.
Kanji choices, spacing and punctuation
Japanese is written without spaces, so the transcript comes out as continuous text with 。 and 、 punctuation. Most corrections are kanji choices: homophones such as 会う and 合う, or 機関 and 期間, sound identical and are picked from context, and personal or company names may get a common but wrong spelling. Numbers can appear as Arabic digits or as kanji.
English loanwords are normally written in katakana, though brand and product names sometimes stay in Latin letters. Polite keigo in business videos and casual speech in vlogs are both handled; dialects such as Kansai-ben are written down, sometimes with standard forms mixed in. There is no furigana and no romaji output.
Japanese video people transcribe
Frequent uploads:
- YouTube talk videos, interviews and finished live streams, for subtitles or quotes.
- University lectures and seminars recorded on video.
- Business meetings and online presentations, for minutes (議事録).
- Japanese study material: a teacher's video turned into a script to read along with.
Japanese subtitles (字幕)
Export SRT or VTT to add Japanese subtitles in YouTube Studio, Premiere Pro, DaVinci Resolve or VLC. The files are UTF-8; if an editor shows boxes instead of characters, pick a Japanese font in its subtitle style. Because there are no spaces, it helps to shorten long lines in the editor before exporting.
DOCX and PDF keep the text for reports or study, and CSV lists each line with its start time.
Accuracy and reading it in English
Clear Japanese speech gives a strong draft. Proper nouns, technical terms and overlapping voices on variety-show style videos need the most attention. Speaker labels are available on paid plans and with a Minute Pack.
The transcript stays in Japanese. For an English reading, open the Google Translate link on the transcript, or use the AI prompt export to hand the text to ChatGPT, Claude or Gemini. For audio-only recordings, see the Japanese audio to text page.