Extract text from scanned documents using neural network OCR — runs entirely in your browser
🔒 Your files never leave your device — AI runs locally
📄
Drag & drop a scanned PDF here, or browse files
OCR Options
AI OCR Engine: Powered by Tesseract.js — a neural network OCR engine trained on 400,000+ samples. Works on scanned documents, photos of text, and image-based PDFs. Text-based PDFs already have selectable text — use PDF to Text instead (faster).