OCR a scanned PDF
Recognize the text in a scanned PDF and download a searchable copy: the pages look identical, but you can now select, copy and search the text. You also get a plain-text export. Recognition runs entirely in your browser — most OCR sites upload your documents; this one cannot.
100% private: files are processed in your browser and never uploaded to any server.
How it works
- Drop a scanned PDF into the box above and pick the document language.
- Click “Recognize text” — the engine loads once, then processes each page on your device.
- Download the searchable PDF, the plain text, or both.
Frequently asked questions
What does OCR actually do to my PDF?
It adds an invisible text layer on top of each scanned page. The page image stays exactly as it was, but PDF readers can now select, copy and search the text underneath the image.
Which languages are supported?
English and Spanish, individually or combined for bilingual documents. The recognition models are served from this site and cached — after the first use, OCR even works offline.
Why is it slower than other OCR sites?
Because nothing is uploaded: your own device does the work. A typical page takes a few seconds. In exchange, confidential documents — contracts, medical records — never leave your machine.
How accurate is the recognition?
On clean scans at 150 DPI or more, accuracy is comparable to commercial tools. Skewed, low-resolution or handwritten pages reduce accuracy — OCR engines only reliably read printed text.