PDF OCR

Extract text from scanned PDFs and images using AI-powered OCR. Free, 100% private — works directly in your browser.

📁 Drop scanned PDF or image here or
PDF, JPG, PNG, WEBP — any scanned document
ℹ️ First use: Downloads ~12MB OCR language model. Subsequent uses are instant (cached). One-time setup per language.

About PDF OCR

OCR (Optical Character Recognition) extracts text from scanned documents, images, and non-searchable PDFs using Tesseract.js with LSTM neural networks. Supports 14 languages. All processing in your browser.

AI-Powered Recognition

Uses Tesseract OCR engine with LSTM neural networks for high-accuracy text extraction from scans.

14 Languages

English, Spanish, French, German, Italian, Portuguese, Dutch, Polish, Russian, Japanese, Chinese, Korean, Arabic, Hindi.

Multi-page Support

Processes all pages of your PDF automatically. Results combined into one text output.

100% Private

All OCR processing happens in your browser using Tesseract.js. Your documents never leave your device. Language data (~12MB) cached after first use.