gUrrT turns lecture videos into a searchable AI tutor
gUrrT is a personal tutor tool for asking questions while watching YouTube or online lecture videos. It picks important video frames, turns audio into text, and uses to describe key frames. That information is stored in a , so the video becomes something that can be searched by meaning.
When someone asks about spoken content or writing on the board, the system finds the relevant video context and sends it to an LLM to produce an answer. The goal is a 24/7 video-learning helper that can run on a consumer-grade PC.
Key points
- The system extracts important frames and audio text from lecture videos.
- add descriptions to key visual moments.
- A stores the processed video information for search.
- Questions retrieve only the relevant video context before calling an LLM.
- This design may help reduce token use for long-video question answering.