OCR PDF
Make a scanned PDF searchable: its words become text you can find and copy.
or drop PDF file here
Stays on your device — nothing is uploadedHow to use OCR PDF
- Choose your PDF file. Or drop it on the page.
- Pick the settings. The defaults suit most files.
- Convert and download. You get a PDF.
Questions
Are my files uploaded?
No. PanPDF does the work inside your browser, so the file never leaves your device. You can even disconnect from the internet after the page has loaded.
Is it free?
Yes, with no account, no watermark and no daily limit. PanPDF is open source.
What does it download?
When you start, the reader (about 3 MB) and the files for the languages you tick (1 to 3 MB each for most), from this site. They are kept only while the page is open and are gone when you leave it. Your PDF is not sent anywhere.
How accurate is it?
It is a very small model, so it can misread; check the text before you rely on it. On clear printed pages we measured about 1 character in 250 wrong for English, 1 in 30 for Thai and 1 in 9 for Lao. Photos that are tilted, dark or blurred read worse.
What reads the text?
Tesseract OCR, compiled for the browser by tesseract.js-core, with the tessdata_fast language models. All three are open source under the Apache License 2.0. The PanPDF desktop program reads with the same Tesseract.
My PDF has a password.
Type it when asked. A file that only forbids printing or copying can be converted without a password.