Make a scanned PDF searchable without uploading
Text recognition (OCR) runs on your device. The pages keep their look, and an invisible text layer lets you search, select and copy.
How to make a scanned PDF searchable
Choose or drop the scanned PDF.
Pick the language of the text and which pages to read. Pages that already have text are skipped.
Recognize the text, then save the searchable PDF or the text as a .txt file.
Frequently asked questions
Is my document uploaded for OCR?
No. The recognition engine and the language model are loaded from DocuChan into this tab, and your pages are read there. The page’s security policy blocks every other connection.
How accurate is it?
Clear, straight scans of printed text usually come out well. Handwriting, tables, decorative fonts, and very small or blurry text can come out wrong or not at all, so check names and numbers.
Which languages can it read?
English, Japanese, Russian, Uzbek (Latin and Cyrillic) and Spanish. The first time in a session, your browser downloads the recognition engine (about 1.5 MB) and the language model you picked (0.8–3.1 MB) from DocuChan: about 2.5–4.5 MB in all.
Are my files uploaded?
No. The PDF is read and changed by code running in this browser tab. The tools page blocks network connections for file processing, so the document, its pages, and any password you type stay on your device.
How large can the PDF be?
Up to 150 MB per file, 300 MB in total when you work with several files, and 500 pages. Very large or complex documents also depend on your device’s memory.
Is it free?
Yes. The PDF tools are free to use, need no account, and add no watermark.