Make a scanned PDF searchable
Optical character recognition finds the text in scanned pages and adds an invisible text layer, so you can search, select and copy. Runs on our server.
or drop files here
PDF files
Where your file is processed
Secure serverProcessed on our secure server over TLS. Files are deleted after download and always within 60 minutes.
How to use OCR PDF
Choose a scanned PDF (up to 50 MB and 100 pages).
Pick English, Vietnamese or both.
Download the searchable PDF.
About this tool
Your scan stays the same
The page images are kept (unless you choose Straighten skewed pages); OCR adds a hidden text layer on top.
Verified result
After OCR we extract the text with an independent reader and tell you how much was found. Recognition quality depends on scan resolution and clarity.
No AI services
Recognition runs with open-source Tesseract on our server. Your text is never sent to third-party or AI services.
Frequently asked questions
Which languages are supported?
English and Vietnamese. Choose both for documents that mix them.
How long does OCR take?
It depends on the number of pages and the scan quality. Jobs are stopped after 3 minutes.
Why was little text found?
Low-resolution, skewed or handwritten pages recognise poorly. Try scanning at 300 DPI.