Google’s own AI service, Gemini, is exceptionally good at analysing images and videos. Paste a YouTube link in the prompt window and Gemini will return in a very short time a text summary of the video content. You can even ask Gemini to just search for that part of information in the video that you are looking for: ask Gemini to find what a presenter says in a long video about for example climate change. Similarly Gemini can also describe images for you, and it is particularly creative in telling stories about what it thinks it sees in the image you upload. However it has its limitations for example in describing people.
Gemini