Help › How to OCR a PDF

How to OCR a PDF (make scans searchable)

A scanned PDF is just pictures of pages — you can't search or copy the text. OCR fixes that by recognising the words and adding an invisible text layer. Here it runs entirely on your device: no cloud OCR service, nothing uploaded.

1. Open the scanned PDF

Open the document in the editor, or start from the OCR PDF page, which runs OCR on the first page as soon as you pick a file.

2. Run OCR on a page

Go to the page you want and choose Document → OCR this page (or the OCR page (searchable text) button in the sidebar). The engine renders the page at high resolution, recognises the words locally — the OCR engine and its language model are served from this site, not a CDN, so it even works offline — and reports how many words it found.

3. What you get

The recognised words are baked into the page as an invisible text layer positioned exactly over the scanned image. The page looks identical, but now you can:

search the page text,
select and copy it,
export it — as .txt or to Word (see Convert PDF to Word).

4. Repeat for the other pages, then save

OCR runs one page at a time, so step through the pages you need and run it on each. Then click Save to download the searchable PDF — the text layer travels with the file and works in any PDF viewer.

Notes: recognition currently uses an English language model, and accuracy depends on scan quality — clean, straight, 200 dpi+ scans work best. Because OCR is local, large pages take a few seconds of your CPU rather than a trip to someone's server.

OCR a PDF now →

More guides: Convert PDF to Word · Edit a PDF · Compress a PDF