OCR
Make scanned PDFs searchable by extracting text with OCR.
How to use OCR
Upgrade to Pro
OCR is available on the Pro plan. Visit the Pricing page to upgrade.
Open the OCR tool
Go to Tools and click OCR.
Upload your scanned PDF
Drop the scanned PDF. The tool recognises that the content is image-based.
Process
Click OCR. The tool runs Tesseract OCR to extract text from each page.
Download
Download the searchable PDF. You can now select text, copy it and search with Ctrl+F.
Tips for best results
OCR accuracy is highest on clean black-and-white scans at 300 DPI or above.
After OCR, use AI Chat or AI Summarize to interact with the content.
The original visual appearance of the document is preserved. OCR adds an invisible text layer underneath the image.
Common questions
How accurate is the OCR?
For clean typed text at 300 DPI or higher, accuracy is typically 97-99%. Handwritten text and low-resolution scans have lower accuracy.
Which languages are supported?
English, Hindi, Tamil, Telugu, Marathi, Gujarati, Bengali, German, French, Spanish, Portuguese, Arabic, Chinese (Simplified) and Japanese. Select the document language from the dropdown before processing for best accuracy.