Extract text from scanned PDFs and images. Powered by Tesseract.js — runs entirely in your browser.
Scanned PDFs, JPG, PNG — any document with text
Max 25MB · PDF, JPG, PNG · Never uploaded to server
Text PDFs: extracted instantly. Scanned/Image: uses Tesseract.js (downloads ~5MB first time).
Starting OCR...
🔗 Summarize this extracted text with AI?