OCR — Make PDFs Searchable
Got a scanned document you can't search or copy text from? Drop it here and we'll read the text for you — right in your browser.
About this tool
Make Scanned PDFs Searchable — Free & Private
Got a scanned contract, a photographed receipt, or a PDF of a printed document? This tool reads the text in those images and makes it searchable, selectable, and copy-pasteable — without uploading your file anywhere.
Search & Find
After OCR, you can use Ctrl+F to search for any word in the document. No more scrolling through pages looking for a specific name or number.
15+ Languages
English, Spanish, French, German, Chinese, Japanese, Korean, Arabic, Hindi — and dozens more. Select your language before starting.
Completely Private
The OCR engine runs inside your browser using WebAssembly. Your document never leaves your computer — perfect for contracts, medical records, and legal filings.
How to OCR a scanned PDF
- 1
Open your scanned PDF
Click "Select Scanned PDF" or drag your document onto the page. It loads instantly — nothing is uploaded.
- 2
Choose the language and start OCR
Pick the language of the text in your document, then click "Start OCR." The engine loads the language data and begins reading each page.
- 3
Review the recognized text
The tool highlights recognized words on each page. You can read through the text preview, copy it to your clipboard, or download it as a .txt file.
- 4
Save a searchable PDF
Click "Save Searchable PDF" to download a version with an invisible text layer. The pages look identical, but now you can search, select, and copy text from them.
Frequently asked questions
What is OCR?
OCR stands for Optical Character Recognition. It's technology that reads text from images — like a scanned page or a photo of a document — and converts it into real, selectable, searchable text that you can copy-paste.
What's a "searchable PDF"?
A searchable PDF looks exactly like the original scanned document, but has an invisible text layer behind the page images. This means you can use Ctrl+F to find words, select and copy text, and the file is accessible to screen readers. The pages look the same — the text is just hidden behind them.
How accurate is the text recognition?
For clean, well-scanned documents with standard fonts, accuracy is typically 95–99%. Handwriting, low-resolution scans, or unusual fonts will produce lower accuracy. The tool shows a confidence score for each word so you can spot potential errors.
Is my file uploaded to a server?
No. The OCR engine (Tesseract) runs entirely inside your browser as WebAssembly. Your document never leaves your device. All the recognition data is hosted on this site — no external servers are contacted.
Why does the first page take longer?
The OCR engine needs to load the language recognition data (~4 MB) when you first click Start OCR. This is loaded from the site itself — no external servers involved. After the first page, subsequent pages process much faster.
Does it work with handwriting?
It works best with printed text. Neat, consistent handwriting may produce usable results, but messy or cursive handwriting will have low accuracy. For best results, use clean scans of printed documents.
Is it free?
Completely free — no account, no watermarks, no limits on pages or documents.