OCR It is a privacy-focused browser extension for Chrome (116+) and Firefox (140+) designed to extract text from non-selectable, paginated digital documents such as scanned books or slide decks. The tool utilizes a bundled Tesseract build to perform all OCR processing locally, ensuring no data or images leave the user's machine. Users can manually capture specific regions using a hotkey (⌥⇧S) or initiate an automated sequence (⌥⇧A) that captures, turns the page, and repeats the process. The automation feature includes an intelligent "next-page" control that uses a fixed coordinate point rather than CSS selectors, allowing it to navigate through complex DOM structures like cross-origin iframes and Shadow DOMs. To ensure accuracy, the extension employs Tesseract's "Auto" layout analysis to correctly handle multi-column text, which can otherwise result in a 52.9% character error rate if misconfigured. The extension supports multiple languages, including English, Portuguese, and Spanish, and can be customized with additional Tesseract models. An automated run concludes automatically if it detects two consecutive identical pages, reaches a default 300-page cap, or encounters an error, preventing infinite loops on the final page.