How to add 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.
When the draft is ready, the player and the text move together. Click a line to replay it and type your correction over the line.
Lingala is low-resource: plan to edit
Lingala is spoken by many millions in Kinshasa, Brazzaville and the Congolese diaspora, but the speech model has seen very little of it. Expect a rough draft: many lines will need rewriting, and some words come out as French or as guesses. It works best on slow, clear speech from one speaker and still saves time on a long video compared with typing from nothing.
Lingala is written in the Latin alphabet, usually without tone marks, which is how the draft writes it. Everyday speech mixes in French constantly, along with words from Kikongo, Swahili and Tshiluba. If a video is mostly French with Lingala phrases, select French and fix the Lingala lines; if it is mostly Lingala, keep Lingala selected.
Lingala videos people transcribe
What gets uploaded:
- Sermons and prayer meetings from Congolese churches in Kinshasa, Brussels, Paris and London.
- Comedy sketches, interviews and news commentary from YouTube and TikTok.
- Family videos and messages, to keep elders' words in writing.
- Your own videos, for Lingala subtitles.
Subtitles and documents
After correcting, export SRT or VTT to add subtitles on YouTube, TikTok or in an editor such as CapCut or Premiere Pro. DOCX, PDF and TXT keep the text for sharing, with or without timestamps. Congolese rumba and other music videos are hard for the model, since singing over instruments is much less clear than speech.
Tips and translation
Choose videos where one person speaks clearly, and turn on audio repair if the room echoes or a crowd responds loudly. Speaker labels are available on paid plans and with a Minute Pack.
The transcript stays in Lingala. 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 Lingala audio to text page.