A scan is a picture, not a document
When you scan or photograph a page, the result is an image. You can look at it, but you cannot select a line, copy an account number, or press Ctrl-F to find a word. OCR (optical character recognition) reads the letters out of the picture and writes them back into the PDF as an invisible layer positioned exactly over each word. The page looks exactly the same — but now it is searchable, copyable, and useful.
Who uses this tool
Anyone who needs to search or copy from a scanned bank statement, agreement, marksheet or old record — and would rather not upload a private document to an unknown server to do it.
How to use it
- Add a scanned PDF, or photos of the pages.
- Click Make it searchable. The engine downloads once, then reads each page on your device — a few seconds per page.
- Download the PDF. It looks the same, but you can now select and search its text.
Photographing pages rather than scanning them? Run them through the Document Scanner first — straightening and cleaning the page makes OCR markedly more accurate.
Honest limits
OCR is good on clear, straight, well-lit scans of printed English text. It struggles with blurred photos, handwriting, unusual fonts and heavy background patterns — and it can misread a character here and there. Always check the result before relying on it for anything that matters.
Frequently asked questions
What does OCR actually do?
It reads the words out of the scanned image and adds them to the PDF as an invisible text layer, so the file becomes searchable and copyable while looking identical.
Is my document uploaded?
No. The recognition engine is downloaded into your browser and runs on your device. The document never leaves your machine.
Why does it take a few seconds per page?
Because your device is doing the work instead of a server farm — that's the trade for never handing over the file.
Does it read Hindi or handwriting?
Not yet — it recognises printed English. Handwriting is unreliable for any OCR engine.