Convert Scanned PDFs and Photos to Text

Extract text from scanned documents, contracts, receipts, and photographed papers.

No cal iniciar sessióEls fitxers es mantenen privats

📦OCR uses ~10 MB of data on first run per language (cached afterwards).

Deixa els fitxers aquí o fes clic per navegar

JPG, PNG, WebP, BMP sense límit de mida de fitxer

Navegar pels fitxers

Els teus fitxers no surten mai del teu dispositiu. Tot el processament es fa localment al teu navegador.

Scanned Documents tips

📄

For multi-page scans, run each page separately. The .txt download per page can then be combined.

💡

Best results: documents with good contrast (dark text on light background), printed (not handwritten), with clean fonts.

🎯

For receipts (often crumpled, light prints), increase image contrast in any photo editor before uploading. Tesseract works much better on high-contrast input.

🔍

Tesseract is comparable to many paid OCR services for printed text. For handwriting, paid AI-based services (Google Vision, AWS Textract) still beat it.