Extract Text from Images and Scanned PDFs

Turn document photos and scanned PDF pages into editable text. Recognition runs on your device in six languages. First use downloads recognition files; review the output for errors.

The interactive tool needs JavaScript enabled.

How to use this tool

1. Upload document photos or a scanned PDF.
2. Choose Extract text, then select the recognition language.
3. Download recognized text as a Unicode .txt file. English, Spanish, French, and German can also be embedded in a searchable PDF.

Frequently asked questions

Which OCR languages are supported?

English, Spanish, French, German, Hindi, and Arabic are available for text downloads. Searchable PDF export supports English, Spanish, French, and German. Hindi and Arabic are currently available as Unicode text downloads only.

Does OCR upload my documents?

No. Recognition runs locally in your browser. Recognition files download on first use; document images are not uploaded.