Extract text from a scanned PDF (OCR)

Recognise the printed text inside a scanned PDF and turn it into text you can copy, search and reuse. The recognition runs in your browser — your file is never uploaded.

Processed in your browser — never uploadedFree · no sign-up

Drop a scanned PDF to OCR

or click to browse

Recognises printed text in your browser — your file is never uploaded.

How to extract text from a scanned pdf (ocr)

  1. 1

    Open your scanned PDF

    Drop your PDF above, or click to browse.

  2. 2

    We read each page

    Pages are rendered and run through OCR right in your browser.

  3. 3

    Copy or download

    Copy the recognised text or download it as a .txt file.

Frequently asked questions

What languages are supported?

English is built in. More languages can be added on request.

Is my file uploaded?

No. OCR runs in your browser; only the recognition model is fetched (once) from a CDN. Your PDF stays on your device.

Will it work on photos of text?

It's tuned for scanned documents. Clear, high-contrast scans give the best results; very faint or handwritten text may not recognise well.

Can I get a searchable PDF back?

Right now it extracts the text; a searchable-PDF export (text layer over the scan) is on the roadmap.

Chat with PDF