Local Toolkits
All Tools
image tool

OCR

Extract text from images and PDFs. Offline.

Browser-based text recognition powered by Tesseract.js WebAssembly. Drop images or multi-page PDFs, extract text in 30+ languages, and export as TXT, PDF, DOCX, JSON, or batch download as ZIP.

FEATURES

What OCR does

30+ languages

Multi-page PDF

5 export formats

Batch OCR + ZIP

Offline via service worker

SUPPORTED FORMATS

.png.jpg.webp.bmp.tiff.gif.pdf

UNDER THE HOOD

How it stays local

Technology Stack

Tesseract.js OCR engine compiled to WebAssembly for near-native text recognition speed

Offline Capable

Works without internet after first load

Zero Upload

Files never leave your browser

WebAssembly Powered

Near-native performance in your browser

Ready to use OCR?

No account required. No download. Just open and start processing.

Launch OCR