PDF OCR

Choose a scanned PDF and get its text back as plain text that you can copy or save as a .txt file. Recognition runs in your browser, so the PDF stays on your device, and the tool reads English text.

Select a PDF to OCR

Drag & Drop or click to select a file (PDF)

How to use OCR PDF

  1. Choose a PDF. The tool starts at once.
  2. Wait while the pages are checked. A page that already has real text is copied as it is. A page that is only a picture goes through OCR.
  3. Read the result in the text box. A note above it says how many pages came from existing text and how many needed OCR.
  4. Copy the text, or download it as a .txt file.

Scanned PDF or text PDF?

A text PDF has real letters inside it. You can select a word with your mouse. A scanned PDF is a photo of paper. The letters are only pixels, so you cannot select or search them. OCR means optical character recognition. It looks at the pixels and works out which letters they show.

A quick test: try to select a word in your PDF. If you cannot, the PDF is scanned.

When people use it

  • Copying text out of a scanned contract, letter or form.
  • Getting the numbers from a scanned receipt or invoice.
  • Reading old documents or book pages that were scanned.
  • Turning a scan into text you can search, edit or translate.

Tips and limits

  • English only for now. Other languages will not read well. Handwriting is usually not read well either.
  • The first run downloads the OCR engine and the English language data, about 11 MB, from docsbee.online. Your browser keeps them, so later runs on the same device start faster.
  • Results depend on the scan. Straight pages, dark text, a clean background and 200 to 300 dpi work best.
  • OCR usually takes a few seconds per page. A phone or an older computer is slower. You can cancel at any time. If OCR makes no progress for 45 seconds, DocsBee stops it and offers a Retry button.
  • The result is plain text. Columns, tables and layout are not kept.
  • If the PDF has a password, remove it first with Unlock PDF.
  • Want a PDF that you can search, not a text file? Use Searchable PDF. To read text from a photo, use Image to Text.

Privacy: what happens to your file

The OCR engine and the English language data load from our own site, and the reading happens on your device. Your PDF and the text it produces are not sent anywhere. Ordinary page requests may appear in our hosting provider's logs.

Frequently asked questions

Which languages does OCR PDF support?

English only at the moment. Text in other languages will be read badly.

Why is the first scan slower?

The first run downloads the OCR engine and the English language data, about 11 MB. Your browser keeps them. Later runs on the same device skip the download.

Does it make my PDF searchable?

No. It gives you the text, not a new PDF. For a searchable PDF, use Searchable PDF.

Is my PDF uploaded?

No. The pages are read on your device.

Can it read a photo or a screenshot?

Use Image to Text for that. It works the same way, with a picture instead of a PDF.