[andrewnguonly]

I haven't tried it, but in general, it accepts any text.

Or are you asking if it can automatically get the transcript from a YouTube video? At the moment, it can't do the latter. I do plan to support multi-modal LLMs (llava via Ollama), but I'm not sure how the mechanics of the extension will work yet. Open issue: https://github.com/andrewnguonly/Lumos/issues/27

[regularfry]

I was thinking specifically about getting it the youtube-provided transcript of a video you're watching, rather than doing the transcription itself. With access to the transcript, I could say to it "find me anything in my browser history related to this subject" (or whatever) and have it understand what I've been watching.

[fragmede]

http://YouTubetranscript.com might be of use here.