VidScript

Extract and interact with text from YouTube videos via OCR and LLM integration.

YouTube has become one of the most widely used platforms for learning and self-development. Whether it's students studying for exams, professionals exploring new skills, or everyday users seeking knowledge, YouTube serves as an ever-growing, visual learning hub. Yet, despite its educational value, extracting and interacting with textual content from YouTube videos remains a frustrating experience. Many videos display crucial information in the form of slides, code snippets, formulas, or diagrams, often for just a few seconds. To capture this information, users are forced to pause the video, take screenshots, and transcribe the text manually. This process is not only time-consuming but also error-prone and disruptive to the learning flow. Worse still, when the content is blurred, low-resolution, or partially obstructed, the challenge of reading and understanding becomes even greater. VidScript is built to solve this everyday problem. It is a lightweight Chrome extension that allows users to pause a YouTube video, select any part of the frame, and extract the visible text instantly using OCR (Optical Character Recognition). Beyond extraction, VidScript enhances the learning experience by using AI to explain the content, translate it, summarize it, or even let users chat about it directly within the video interface. This tool is designed for anyone who uses YouTube as a source of learning because extracting knowledge from videos shouldn't be a struggle.