OCR PDF
Turn scanned PDFs and images into selectable, searchable text.
Drop a PDF or image to extract its text
Scanned PDFs and photos become selectable, copyable text. Everything runs in your browser; nothing is uploaded.
OCR runs 100% in your browser with Tesseract. The first run downloads the engine and language data (cached for next time). Your file is never uploaded.
How it works
Run OCR on a scanned PDF or a photo and get real, selectable text you can copy, search and edit. Recognition uses Tesseract and happens entirely in your browser — the file is never uploaded to any server, so it is private and free. Pick the document language for the best accuracy.
Frequently asked questions
What is OCR?
OCR (optical character recognition) reads the text inside images and scanned pages and turns it into real, selectable text.
Is my file uploaded to a server?
No. OCR runs 100% in your browser with Tesseract; the file never leaves your device.
Which languages are supported?
English, Spanish, French, German, Portuguese and Italian, plus a combined English + Spanish mode. Choosing the right language improves accuracy.
Does it work with photos too?
Yes. You can drop a PDF or an image (JPG, PNG, WebP). Clear, well-lit scans give the best results.