I want to prompt a YT video to the API. How can I do that? I also want to do it inside Next.js. Would this require downloading the video, and then uploading?
The vision APIs don’t directly support video. You’d have to break the video into individual frames and send them to the model frame by frame.
The other approach is to just use the transcript. There are a number of services out there that let you get the transcript from a YT video but YT is pretty aggressive about blocking those services.
3 Likes