Optical Character Recognition

Optical Character Recognition is a handy tool that lets you extract text from images, videos, or PDFs with just one click and a quick crop—instead of retyping everything character by character. Whether it is a screenshot, a slide, or a frame from a clip, the text you need is only a click away.

A typical use case is copying any text from YouTube videos or tutorials saved as images, which is a real time-saver when you want to quote, translate, or take notes from content that you cannot select directly.

Under the hood, Optical Character Recognition copies text from images using Tesseract.js, a lightweight OCR engine, so the whole process stays fast and smooth in your browser.