How to use PDF OCR
- Choose a scanned PDF or a PDF made from photos.
- Tick the languages used in the document.
- Press Recognize text and download a searchable PDF or a plain text file.
Text recognition that never leaves your device
OCR (optical character recognition) reads the letters in a scanned image and adds an invisible text layer, so you can search, select and copy. The first time you use it, your browser downloads a free recognition engine and language pack. Your document itself is processed on your device and never sent anywhere.
Private by design
PDF OCR runs entirely in your browser. Your file is processed on your own device and is never uploaded to a server, there's no sign-up, and the result is ready to download as soon as it's done.
Questions
Which languages are supported?
English, Arabic, Hindi, Urdu, French, Spanish, German, Portuguese, Russian, Chinese, Turkish and Indonesian. You can tick more than one.
How long does it take?
About 5–20 seconds per page, depending on your device. Long documents take longer.
Why does it download something the first time?
That is the recognition engine and language data. Only the engine is downloaded. Your PDF stays on your device.