Skip to content

Desktop app

OCR PDF: make a scanned PDF searchable

Coming to the PDFCheetah desktop app

Make a scanned PDF searchable by reading the words in its pictures, in the desktop app.

What it will do

OCR PDF will read the words in a scanned PDF — pages that are really photographs of paper — and put an invisible text layer behind each page. You can then search the PDF, select and copy its words, and have a screen reader read it aloud. The pictures of the pages stay exactly as they were.

This is what people mean by PDF OCR, or by making a PDF searchable. It will run in the PDFCheetah desktop app, on your own computer, with nothing uploaded.

Why it needs the desktop app

Reading text out of a picture takes a recognition engine and a trained model for each language, which are large to download, and recognizing page after page of a long scan is heavy work that a browser tab does slowly.

The desktop app installs the engine and the languages you need once, and runs them at your computer's full speed. Your scans never leave it.

Check whether your PDF needs OCR at all

Many PDFs already carry their words. A PDF saved from Word, a web page or an email has text in it; only scans and photographed pages do not. You can tell in a few seconds.

  • PDF to Text. For a PDF that already has text: copies every word out as plain text, free, in your browser.
  • Summarize PDF. For a PDF that already has text: picks out its key sentences, each with its page.

Does it already have text?

  1. Open the PDF in any viewer, such as your browser, Preview or Adobe Acrobat Reader.
  2. Drag across a single word, as if to select it.
  3. If just that word highlights, the PDF has text, and PDF to Text below copies all of it out.
  4. If dragging draws a box over the whole page, or Find (Ctrl+F, or Cmd+F on a Mac) cannot find a word you can see, the page is a picture and needs OCR.

A scan, today

  1. Upload the PDF to Google Drive.
  2. Open it with Google Docs, which reads the words in the scan into a new document.
  3. Check the result against the page: recognized text has mistakes, most of all in tables and handwriting.

This way uploads your file to Google Drive. The others on this page work on your own computer.

Nothing on this page reads a scan today, and PDFCheetah's web tools cannot read the words in a picture: PDF to Text finds nothing in a page that is only an image.

The desktop app

The PDFCheetah desktop app is being built for Windows, macOS and Linux, to do the work a browser tab cannot, on your own computer. Its download page goes up when the app is published.

One email, when this tool is ready in the desktop app. No newsletter, and we do not pass it on.

Common questions

Is OCR PDF free?
Local OCR is planned as part of Pro in the desktop app, which has no price yet, so there is nothing to buy here. PDF to Text, for PDFs that already have text, is free today.
Is my file uploaded?
No. Nothing on this page takes a file, and the desktop app will read your scans on your own computer. Of the ways above, only Google Drive uploads your file.
When will it be ready?
There is no date yet. Leave your email above and we will send one message when it is ready in the desktop app.