What does OCR PDF do?

It reads text from scanned PDF pages and adds an invisible searchable layer so you can select, copy and search the document.

Which languages are supported?

English, Hindi, Marathi, and English + Hindi combined. Choose the language that matches your document before running OCR.

Are my PDFs uploaded to a server?

No. OCR runs entirely in your browser using pdf.js and Tesseract.js. Your file never leaves your device.

OCR PDF

Advanced OCR for scanned PDFs - per-page control, image preprocessing, confidence scores, and searchable PDF export.

🔒 Files never leave your browser

Step 1

Upload PDF

Drop your scanned PDF here

or use the button below to browse files

PDF only Max 50 MB Up to 30 pages

Step 2 OCR settings (Optional)

Language

Render DPI

Page range

Advanced OCR settings

Preprocessing

Page layout (PSM)

Auto-detect and correct page rotation

Auto mode: skip pages that already have selectable text

Click page thumbnails to cycle Auto → Force OCR → Copy only. Range examples: 1-5, 1,3,8. First run downloads language data (~15–50 MB, cached).

OCR PDF

Upload PDF

Run OCR

Pages click mode · rotate · remove

Searchable PDF ready

Related PDF tools