Generating video insights based on machine-generated text representations of videos

A computing system comprising:

• a processor;
• and
• computer storage memory having computer-executable instructions stored thereon which, when executed by the processor, configure the computing system to perform operations comprising:
• obtain text data associated with a video, the text data including a first type of text comprising a transcription associated with the video, a second type of text comprising a metadata associated with the video, and a third type of text based on analysis of a frame of the video;
• generate a first model prompt to be input into a large language model, the model prompt including the text data associated with the video;
• obtain, as output from the large language model, a text representation that represents the video in natural language based on the text data including the first type of text, the second type of text, and the third type of text;
• and
• generate a second model prompt, including the text representation and an indication of a type of desired video insight, to be input into a machine learning model to generate the desired video insight that indicates context of the video.