Uploading a Latin video
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 draft opens with a player beside it. Clicking a line replays exactly that phrase, which matters when you are checking an ending or a quoted verse.
An honest note on spoken Latin
Very little spoken Latin exists compared with living languages, so the model has seen little of it. Treat the output as a rough draft: case endings, elisions and less common vocabulary are frequently wrong, and the text can slide toward Italian or English spellings. Slow, clearly read Latin from one speaker gives the best results; sung chant and polyphony give poor ones.
Pronunciation also varies. Ecclesiastical Latin, used in church, sounds Italian (caelum with a ch-like c), while the restored classical pronunciation used in many classrooms keeps a hard c and a w-like v. Both are written the same way, and the draft uses plain letters without macrons. If a video is an English lecture with Latin quotations, select English and fix the quotations by hand.
Latin videos people transcribe
Typical sources:
- Traditional Latin Masses and readings, to follow or check the text.
- Spoken-Latin YouTube channels and conversational Latin classes.
- Students reciting set texts, for teachers checking pronunciation and wording.
- Papal addresses and Vatican ceremonies with Latin passages.
Latin subtitles and documents
Once corrected, export SRT or VTT for subtitles on YouTube or in a video editor, so learners can read along. DOCX and PDF keep a printable text for class, and TXT drops into notes. Timestamps can be turned on to mark where each line falls in the video.
Making the draft useful
Use the draft for timing and structure, then correct against the printed text if one exists, such as a missal or an edition of the author. That is often faster than typing from the video alone. Speaker labels are available on paid plans and with a Minute Pack.
The transcript stays in Latin. 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 Latin audio to text page.