100% Client-side

OCR PDF

Extract text from scanned PDFs and images using optical character recognition. Everything runs in your browser.

or image, or drop it here

PDF, JPEG, PNG, WebP

How to use

📄

1. Upload file

Select a scanned PDF or image (JPEG, PNG).

🔍

2. Auto-OCR

Tesseract.js reads the text from your document.

📋

3. Copy or download

Copy the extracted text or save as a .txt file.

What file types does OCR support?

Scanned PDFs, JPEG, PNG, WebP, and TIFF images.

Are files uploaded?

No. OCR runs entirely in your browser using Tesseract.js. Nothing is sent to any server.

How accurate is the OCR?

Accuracy depends on scan quality. Clear, high-resolution scans typically achieve 95%+ accuracy.

Is there a page limit for PDFs?

Currently, the first 10 pages are processed. Full document OCR is coming soon.