OCR PDF (make PDF searchable)

To make a scanned PDF searchable, choose the file, pick the language of the text and press Make PDF searchable. Every scanned page is read with OCR on your device and the recognised words are placed, invisibly, exactly over the picture, so the PDF looks the same but you can search, select and copy its text.

  • ๐Ÿ”’ Runs on your device
  • โค’ 0 bytes uploaded
  • โœ“ Free, no sign-up, no watermark
  • โฌ‡ 9 MB engine, downloaded once
Loading the toolโ€ฆ

How to use OCR PDF

  1. Choose the scanned PDF.
  2. Pick the language of the text (English, French, Spanish, Portuguese, German, Italian, Russian, Arabic, Hindi, Chinese, Japanese or Korean).
  3. Press Make PDF searchable and wait while each page is read.
  4. Download the searchable PDF.

About OCR PDF

Each page is drawn at 300 DPI with pdf.js and read by Tesseract 5 (LSTM models). Every recognised word is written as invisible text (text rendering mode 3) at its position, stretched to the width of the word in the picture, with a font that has its characters (Liberation Sans, Noto or IBM Plex for other scripts), so selecting text highlights the right words.

To get the text itself rather than a searchable PDF, use PDF to Text or PDF to Word: both can read scanned pages with OCR too.

Is it private?

Yes. OCR PDF runs entirely in your web browser using your device's own processor. Your files never leave your device: they are not uploaded to Nolo or anyone else, and the page's security policy only allows it to talk to nolotools.com, which accepts no files. The site sends only two small things: the words typed in the optional search box, to find a tool, and, the first time you use a tool on a page, that tool's name for an anonymous daily count of tool use (nothing about you, your files or what you typed). Results are kept encrypted on your device for 60 minutes in Your files, then deleted automatically, or straight away with Delete all. How Nolo works.

Questions and answers

Is my PDF uploaded for OCR?

No. The text recognition engine (Tesseract, as WebAssembly) runs in your browser. The PDF and its text never leave your device.

Does the PDF look different afterwards?

No. The pages are not re-drawn or re-compressed; Nolo only adds invisible text on top of each scanned page, the way Acrobat's "Recognize text" does. Search, select and copy then work in any PDF viewer.

Which languages are supported?

English, French, Spanish, Portuguese, German, Italian, Russian, Arabic, Hindi, Chinese (simplified and traditional), Japanese and Korean. Each language is a 1 to 3 MB download the first time you use it.

What about pages that already have text?

They are skipped, so digital pages are not duplicated. Turn on "Also read pages that already have text" to read every page anyway, for example a scan that already has a poor text layer.

How accurate is it?

Clean printed scans at 200 to 300 DPI are usually read almost perfectly. Photos taken at an angle, low resolution, handwriting and decorative fonts give worse results. Nolo shows the average confidence.

How long does it take?

A few seconds per page on a laptop, longer on a phone. Everything runs on your device.