Make a scanned PDF searchable (OCR)
Recognise the text in scans so you can search and copy it.
Processed on your deviceor drop a PDF anywhere on this page. Files stay on this device.
How to make a scanned PDF searchable (OCR)
To make a scanned PDF searchable, open the file and press Recognise text. Puffin PDF reads each page on your device and adds an invisible text layer behind the scan, so the pages look the same but can be searched, selected and copied. The first run downloads the recognition model (about 15 MB) to your browser.
- Select a scanned PDF, or drop it on this page.
- Press Recognise text and wait while each page is read.
- Download the searchable PDF.
Questions and answers
How accurate is it?
Clean, printed scans in Latin-script languages are read well. Handwriting, very small print and poor photos are harder. High-accuracy OCR for hard scans is a Pro feature arriving after launch.
Does the page look different afterwards?
No. The recognised text is invisible and sits behind the page image. Only searching, selecting and copying change.
Why does the first run take longer?
The recognition model is downloaded from our site to your browser the first time (about 15 MB) and kept for later. Your scan is not uploaded at any point.
Which languages are supported?
English and other languages written in the Latin alphabet, plus digits and common symbols.
Are my files uploaded?
No. The work is done by code running in your browser, so your file never leaves your device. You can check this yourself: open your browser's developer tools, switch to the Network tab and run the tool. No request carries your file.