←back to thread

666 points georgemandis | 1 comments | | HN request time: 0.246s | source
Show context
mt_ ◴[] No.44382623[source]
You can just dump the youtube link video in Google AI studio and ask it to transcribe the video with speaker labels and even ask it it to add useful visual clues, because the model is multimodal for video too.
replies(1): >>44383325 #
MaxDPS ◴[] No.44383325[source]
Can I ask what you mean by “useful visual clues”?
replies(1): >>44384694 #
1. mt_ ◴[] No.44384694[source]
What is the speaker showcasing in its slides, what is it's body language and so on.