OCR scanned PDFs and images

No. Every page is drawn and read inside your browser, by a text reader this site serves; the first page you read downloads the reader from this site, once, and the page says how much before it does. Your files never leave your device.

Printed text on clean scans and sharp photos of pages, upright, sideways or upside down (a page that reads poorly upright is read again turned). It does not read handwriting, and it reads poorly from blurred, low-resolution, curved or shadowed pages, decorative fonts and text over pictures. A table's cells are put in the text row by row. Lines read with low confidence are listed for checking (the reader scores whole lines, not words). A page takes about 2 to 11 seconds on the desktop computers we tested, in Chrome, Firefox and Safari's engine, and the first page also waits for the reader to download; phones and Safari on a Mac, iPhone or iPad have not been tested.

Your pages as they were, with the text read from each laid over it, invisible, where it was read: a PDF reader then finds, selects and copies the text. A PDF's pages are copied whole; each picture becomes a page of its own, at 300 dpi.

Yes: the text is shown after reading, with the lines read with low confidence listed; choose one to jump to it. Your corrections go into the .txt download. The searchable PDF keeps the text as it was read.

PaddleOCR's PP-OCRv6 tiny models, by PaddlePaddle (Apache-2.0), run by eSearch-OCR (Apache-2.0) on ONNX Runtime Web (MIT, with third-party notices), on your device's processor. This site serves them unchanged, with their licences, and loads them only when you read a page.

No. The page loads a PDF engine into your browser and every operation runs on your device. You can check this yourself in the browser's network panel: after the page has loaded there are no upload requests. Closing the tab discards the file.

No. These basic tools are free and never add a watermark. The only limits are the tool's own: up to 100 pages a run and pictures up to 16,384 pixels on a side; English and Simplified Chinese; printed text, not handwriting. Within them, the practical limit is your device's memory.

Encrypted PDFs cannot be processed here. Remove the password first, then use this tool.

Nothing you open or type. While the tab is open, the tool pages keep a short list of the steps taken in it, in the tab's session storage: the step (page opened, started, succeeded, first success, used again or failed), the tool's name, the time, how many files were used and, for a failure, an error code; never a file name, the contents of a file or your text. It holds at most the latest 200 steps, and the browser deletes it when the tab closes. The page never sends it. Where a Report a problem button is shown, you can attach the last 20 steps to your report; nothing is attached unless you tick that box. In local storage the page keeps only choices you made: a Light or Dark theme until you choose System again, the language you picked with the EN / 中文 switch if it differs from your browser's language, and this tool in your recently used list if you switched that list on at the tools page.