OCR PDF
Turn a scanned document into text. Optical Character Recognition runs entirely in your browser to read text from images of pages.
Drag & drop or click to choose
Choose a scanned PDF
Files are processed on your device and never uploaded.
How to ocr pdf
- 1Upload a scanned PDF.
- 2Start OCR — the first run downloads the recognition engine.
- 3Copy or download the recognized text.
Read text from scanned PDFs with OCR
A scanned document is really just a picture of text — you can see the words, but you can’t select, search or copy them. OCR (Optical Character Recognition) fixes that by recognising the letters in the image and turning them back into real, usable text. Upload a scanned PDF and OCR PDF reads it page by page.
Once recognised, you can copy the text or download it, ready to edit, search or paste elsewhere.
Runs privately on your device
Unusually for OCR, this all happens in your browser. The recognition engine downloads once (a few megabytes) on the first run, then processes your pages locally — your scanned documents are never uploaded. Cleaner, higher-resolution scans give the most accurate results.
For digital (non-scanned) PDFs, Extract Text is faster; to get an editable document, PDF to Word can OCR and build a .docx.
Frequently asked questions
Why is the first run slow?+
The OCR engine and language data download once (a few MB), then it runs locally. Accuracy depends on scan quality.
Which language does it read?+
English by default. Cleaner, higher-resolution scans give better results.
Are my scanned files uploaded?+
No. OCR runs entirely in your browser, so even sensitive scans stay on your device.