OCR PDF

Recognize text on scanned PDF pages and download it as text.

Add a PDF to get started

Drag and drop files here, or choose from your device.

Choose PDFChoose a file to add it to this workspace.

A practical guide

How to use OCR PDF

Choose a PDF and select pages to recognize.
Run local OCR on the selected pages.
Review the recognized text and download a UTF-8 TXT file.

Recognize text from page images

OCR PDF reads printed text from selected pages and creates a text file. It does not add a searchable text layer to the PDF. Scans that are unclear, skewed or low contrast may produce errors; check important text.

Processing and limits

OCR runs locally in your browser with the bundled language model. PDFs can be up to 100 MB and 2,000 pages; you can recognize up to 40 selected pages per job. Handwriting is not a supported use case.

Frequently asked questions

Does this make the original PDF searchable?

No. OCR PDF downloads recognized text as a TXT file. Use OCR to Searchable PDF to add a searchable text layer to the PDF.

How accurate is OCR?

Results depend on image clarity and text quality. Review important names, numbers and passages against the page.