OCR Scanner

OCR. Extract Text from Scanned PDFs

Extract editable text from scanned PDFs and images, and get a searchable PDF back.

Select File
①Select file→②Scan→③Copy text

OCR scanned PDFs and images to extract their text, in any of 20 languages from English and Turkish to Arabic and Japanese. You get plain text to copy and a searchable PDF that keeps the original pages with the words behind them.

How to make a scanned PDF searchable

  • Document language: pick the language the pages are written in, from the 20 the reader knows. Its language data is fetched once, the first time.
  • Extract Text (OCR): reads every page and gives you the text and a searchable PDF, the original pages with the words behind them.

Frequently asked questions

Which languages does the OCR engine support?
English, Turkish, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Swedish, Indonesian, Vietnamese, Russian, Ukrainian, Arabic, Hindi, Thai, Chinese (Simplified), Japanese and Korean, plus Turkish with English together for mixed documents. Pick the language your document is written in; its language data downloads once.
Can I edit or search the text after OCR processing?
Yes. Copy the text, save it as a .txt file, or download a searchable PDF. The Privacy Scan button sends the text to our privacy scan, which can pass sensitive words on to Redact.
Can I extract text from a photograph or screenshot?
Yes. Upload an image (JPG, PNG, or WebP) or a scanned PDF, and the OCR engine will analyze the visual content and extract all recognizable text into selectable, copyable format.
How accurate is the text recognition?
Accuracy depends on the scan. Clean, straight, printed pages read well; handwriting, very small print, stylized fonts and faint or tilted scans give more mistakes. Check names and numbers before you rely on them.
Does OCR preserve the original page layout?
OCR returns the text, not the layout. Reading order is preserved line by line, but columns, tables and images are not reconstructed, and the original PDF is left untouched.
Can I OCR a multi-page scanned PDF?
Yes. Upload your multi-page scanned PDF and the OCR engine will process each page individually. The output will be a single searchable PDF with all pages processed.
Is the OCR processing done locally or on a server?
The OCR engine runs entirely within your browser using WebAssembly technology. Your scanned documents are never uploaded to any external server, ensuring complete privacy.

You might also need: