Document Text Extraction (Get Text) is a no-login text extraction tool that pulls plain text out of images, screenshots, and PDF files. Designed as the lowest-barrier entry point so visitors who haven't registered yet can immediately experience the platform's value. Typical use cases include quickly converting paper notes photographed on a phone into editable text, lifting long passages out of webpage screenshots, or pulling specific paragraphs out of PDFs for further editing elsewhere. Functionally similar to ocr but lighter — no layout analysis or language detection, just outputs all text visible in the frame. Runs on local, making it ideal as a landing-page tool to drive sign-ups. For more precise layout recognition or multi-language handling (e.g. preserving table structure, correctly processing vertical Japanese text), register and switch to the ocr module. Output pairs naturally with sc2tc / tc2sc for script conversion, or with translate_to_english / translate_to_tc for translation, completing the paper-to-digital workflow in one go.