Recognise Text (OCR)

Read scanned pages and add a searchable text layer.

Runs in your browser

Drop a scanned PDF

or tap to begin

Any size. Handled on your device.

How it works

  1. 1Open a scanned PDF — one where you cannot select any text.
  2. 2Choose the language of the document so recognition uses the right character set.
  3. 3Run recognition and watch progress page by page.
  4. 4Export the PDF, now carrying an invisible text layer.

What this does to your file

Each page is rendered to an image, passed through a recognition engine running inside your browser, and the recognised words are written back as an invisible text layer positioned over the original artwork. The page looks identical but becomes searchable and selectable.

Common questions

Is my file uploaded to a server?

No. The page loads a PDF engine into your browser and the document is read from disk by that engine. There is no upload endpoint, and once the page has loaded you can disconnect from the network and the tool still works.

How accurate is the recognition?

Accuracy depends on the scan. Clean, straight, high-resolution pages in a common typeface read well; faint, skewed or handwritten pages read poorly. Nothing here corrects the text for you, so proofread anything that matters.

Why is it slower than an online service?

The recognition runs on your own processor rather than a server farm. That is the trade for the document never leaving your device.

Does it change how the page looks?

No. The recognised text is invisible and sits behind the existing page image.

Often used next