OCR PDF

Read the text in scanned pages, so you can search, select and copy it. Also saves the text.

Files are processed on this device and never uploaded.

Drag a file here, or choose one from your device.

Guide

About OCR (make searchable)

Scanned PDFs are pictures of pages: you cannot search them, select a sentence or copy a figure. OCR reads the text in those pictures and adds an invisible text layer, so the PDF looks the same but behaves like a normal document.

Recognition runs on your device. For contracts, medical letters and bank statements, that means the text of your document is never sent to an online service.

Use it to make a scanned PDF searchable, convert a scanned document to text, copy text from a scan, or turn an image PDF into selectable text.

How to use it

  1. Choose the scanned PDF.
  2. Pick the pages to read, or leave it on all pages.
  3. Press Recognise text and wait while each page is read; progress is shown per page.
  4. Download the searchable PDF, and the extracted text as a separate .txt file if you want it.

Good to know

  • OCR currently recognises English.
  • Accuracy depends on the scan: straight, sharp pages at 300 dpi give the best results.
  • Very large pages are read at less than 300 dpi to keep memory use reasonable.

Questions and answers

What does OCR do to my PDF?

It adds a hidden layer of text exactly over the words in the scan. The page looks the same, but you can now search, select and copy it.

Which languages are supported?

English at the moment.

How can I get better OCR results?

Scan at 300 dpi, keep pages straight and well lit, and avoid heavy compression. Clean scans are read far more accurately.

Is OCR done online?

No. The recognition engine runs in your browser, so the document and its text stay on your device.