PDF OCR
New
Extract text from scanned PDFs using OCR
Browser-only · 100% privateUp to 30MBAccepts: .pdf
Loading tool…
Frequently asked questions
PDF to Word extracts existing text layers. PDF OCR reads scanned pages (which are just images) using optical character recognition — for PDFs with no text layer at all.
Accuracy depends on scan quality — clean, high-resolution, well-lit scans work best. Handwriting isn't supported.
No — OCR runs on-device in your browser using a downloaded language model. Nothing is sent to a server.
The first run downloads a language model (a few MB), then each page takes a few seconds to process, depending on your device.