OCR It: Turn un-copyable documents into text for your LLM

OCR It – pull text out of un-copyable documents for your LLM

OCR It is a Chrome extension that extracts text from paginated documents trapped in viewers—scanned books, slide decks, PDFs—where selecting text is impossible. Pin a screen region once, then press a hotkey on each page to capture, OCR, and append text to a running transcript. Or start an auto-run that captures, turns the page, and repeats until the document ends. OCR runs 100% offline via a bundled Tesseract build, with no API keys, no network, and no images leaving your machine. It even handles cross-origin iframes and Shadow DOM for page turning, and exports clean text ready for LLMs like Claude or ChatGPT.