OCR scanned PDF
Runs entirely on your device. Large scans take a while — roughly a few seconds per page.
Ad slot — 728×90
How to OCR a scanned PDF — private & free
- Choose a scanned PDF or a photo (JPG/PNG) of a document.
- Pick the document language and the output: searchable PDF, Word, or text.
- Click "Recognize & download". The OCR engine downloads once (a few MB) and runs on your device.
Frequently asked questions
Is my scanned document uploaded for OCR?
No. Text recognition runs in your browser with Tesseract compiled to WebAssembly. The engine and language data are downloaded from a CDN once; your document is never sent anywhere.
What is a searchable PDF?
Your original scan, unchanged, with an invisible text layer placed over each word. It looks identical but you can search, select, and copy the text, and other tools can index it.
How accurate is it?
Good on clean, straight scans at 200 DPI or higher in the selected language. Handwriting, skewed photos, and low-resolution scans reduce accuracy. Proofread the output for anything important.