OCR PDF

Make scanned PDFs searchable and selectable.

Select a scanned PDF

The first run downloads an OCR engine (a few MB) — after that it works offline

Click to choose, or drop a file here

About OCR for scanned PDFs

A scanned PDF is really just a picture of a page — you can't select or search the text. OCR (optical character recognition) reads those pictures, works out what the words are, and adds an invisible text layer behind the image so the document becomes searchable and copy-pasteable.

PDFCure runs OCR with Tesseract compiled to WebAssembly, so recognition happens on your device with nothing uploaded. It works best on clean, straight, reasonably high-resolution scans of printed text; heavily skewed pages, handwriting, and low-quality faxes are harder and may need a server-grade engine for good results.

How to OCR PDF

1
Open the tool
Open the OCR PDF tool and drop your file onto the page, or click to browse for it. Everything runs in your browser — the file is never uploaded.
2
Run text recognition
Click Start — the tool reads the text in your scanned pages and adds a searchable, selectable text layer.
3
Download the searchable PDF
Download the PDF; you can now select and search its text.

Related PDF tools

Compress PDFShrink file size by re-encoding page images.Compress to Target SizeShrink a PDF down until it fits under a size you choose — for email or upload limits.Repair PDFAttempt to rebuild a damaged PDF.Accessibility CheckerScan a PDF for the concrete things that block screen readers — missing tags, no language, no title, and more.

OCR PDF — frequently asked questions

Will this change how the page looks?+

No — the original page image is kept exactly as-is. The recognized text is layered in invisibly underneath, so nothing changes visually, but you can now select, search, and copy the text.

How accurate is the text recognition?+

It depends heavily on scan quality and the language you select — clean, high-resolution scans in the correct language recognize very well, while skewed, low-resolution, or handwritten pages will have more errors. Make sure to pick the right document language before running it.

Does this upload my file anywhere?+

No — recognition runs entirely in your browser using a WebAssembly OCR engine. The only network activity is a one-time download of that engine and its language data, the same way this site's PDF viewer fetches its own rendering engine; your document itself never leaves your device.

Do you upload my files to a server?+

No — every tool here processes your files entirely on your device, and nothing is uploaded to a server. The only exception is the AI tools, which send the extracted text (not the file) to Claude to do their work.

Is there a file size limit?+

There's no artificial limit we impose, but since processing happens in your browser, very large files (500+ MB or 1,000+ pages) are limited by your device's memory rather than by us.