Bringing in the 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 runs beside the player. Click a line to listen again and rewrite it; changes save as you type.
A rough draft, often pulled toward French or Catalan
Occitan has very little transcribed speech for the model to learn from. Expect a rough draft: many words will come out in French or Catalan spelling, and some lines will need rewriting entirely. It still gives you timing and structure, which saves time on a long video, and it works best on slow, clear speech from one person.
Occitan has several dialects, including Provençal, Languedocien, Gascon, Limousin, Auvergnat and Vivaro-Alpine, and two spelling traditions: the classical norm and the Mistralian norm used by many in Provence. Choose one convention when correcting and apply it throughout. Speakers in southern France switch to French constantly; Aranese speakers in the Val d'Aran switch to Spanish or Catalan. For a mostly French video with some Occitan, select French and fix the Occitan lines by hand.
Occitan videos people transcribe
Examples:
- Interviews with older native speakers, for heritage and dialect archives.
- Occitan-language TV segments and local news.
- Lessons and talks from Occitan schools and associations.
- Theatre, storytelling (contes) and festival speeches.
Subtitles and exports
After correcting, export SRT or VTT to add Occitan subtitles on YouTube or in a video editor; accented letters such as à, è, ò and ç display correctly from UTF-8. DOCX and PDF suit archives, and CSV gives one row per line for research.
Tips and translation
Record close to the speaker and switch on audio repair for village halls with echo. Sung pieces are harder than speech. Speaker labels are available on paid plans and with a Minute Pack.
The transcript stays in Occitan. 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 Occitan audio to text page.