Extract text from an image or PDF (OCR)

About this tool

Pull text out of a photo, a scan or a PDF. PDFs with real text are read directly, and images or scanned pages go through OCR that runs in your browser. Nothing is uploaded, and the language data is bundled with the page.

How to extract text from an image or PDF (OCR)

1. Choose an image or PDF.
2. Pick the language or languages in the document and, for PDFs, the pages.
3. Run the extraction, then copy or download the text.

Frequently asked questions

Which languages are supported?

English, Arabic, Persian, Urdu and Hindi.

How accurate is the OCR?

It depends on the scan. Clear, straight, high-resolution images work best, and you should always proofread the result.

Is my document uploaded for OCR?

No. Recognition runs locally in your browser.

Related tools

• PDF to WordEditable .docx from text
• PDF to imagesSave every page as PNG or JPEG
• Edit imageCrop, rotate, resize and adjust
• PDF to ExcelTables and text into .xlsx
• Images to PDFTurn photos into one PDF

Guides and shortcuts

• How to convert a PDF to Word and what to expect
• How to extract text from a scanned document