Pages that already have real text are copied exactly, without OCR.

Do my files leave my device?

No. Text is read in your browser. The OCR engine and language data are downloaded once, then your files are processed and stay on your device.

Which languages work?

More than 40, including Chinese, Japanese, Korean, Arabic, Hindi and Russian. Each language downloads the first time you use it.

Read the text from a scanned PDF, page by page.

Drop a PDF hereor paste with ⌘V. Your files stay on your device.

PDF

Languages

Engine

1Drop a PDF.
2Pages with a text layer are copied as they are; scanned pages are read with OCR.
3Copy the text or download it, page by page or as one file.

Good to know: Pages that already have real text are copied exactly, without OCR.
Do my files leave my device?: No. Text is read in your browser. The OCR engine and language data are downloaded once, then your files are processed and stay on your device.
Which languages work?: More than 40, including Chinese, Japanese, Korean, Arabic, Hindi and Russian. Each language downloads the first time you use it.

Ready-made settings for common jobs.

More ways to get text out of files.

Search and copy scans

Photos, screenshots, scans

Many files, one zip