OCR PDF Online
Your scanned PDF turns into a file where search and copying work. The recognized text also shows up on its own, ready to copy.
Files are processed on your device and never uploaded to a server.
- Choose PDF
- Choose the language
- Download PDF
Recent results
The first time, the browser downloads a 20 MB neural network. After that it works offline.
Running OCR…
The graphics card is not available for the neural network on this device, so the processor does the work. It takes longer, but the result is the same.
Done! Your PDF is searchable
What's next?
More things to do with your PDF
How to use
- Click "Choose PDF" or drop the scan onto the page. On a phone, the file can be up to 100 MB.
- Choose the document language, English by default, and click "Run OCR". The first time, the browser downloads text recognition, 4 to 20 MB depending on the language.
- Click "Download PDF". For the text alone, copy it from the box or click "Download TXT".
What a searchable PDF is
It's the same scan plus an invisible layer of text. The page images stay untouched, and the recognized words sit right under them. So Ctrl+F works in the file, and you can drag the mouse over a line to copy it.
We opened the results in pdf.js and PDFium, the PDF engines inside Firefox, Chrome and Edge. Pages that already contain text are skipped: their text is kept from the file.
When OCR on a PDF gets words wrong
Dark and crooked scans lead to more mistakes, and tiny print is harder to read. Handwriting isn't recognized. Pick the language the document is written in, since it decides which neural network reads the letters.