OCR PDF
Turn scanned PDFs and photos into selectable, copyable text โ right in your browser.
Drag & drop a scanned PDF or image here, or click to choose. OCR runs entirely in your browser โ your file is never uploaded.
Recognition options
Private by design: the language model (trained data) is downloaded once from the CDN โ your document stays on this device.
OCR PDF reads scanned PDFs and image files (PNG/JPG) and extracts the text inside them so you can copy, edit, and search it. Recognition runs entirely in your browser using Tesseract, so your document never leaves your device โ only the language model is downloaded once. Pick from English, Spanish, French, German, Portuguese, Italian, Hindi, Arabic, Chinese, and Russian, then copy the result or save it as a .txt file. For best accuracy, use clear, high-resolution scans; printed text recognises far better than handwriting.
Frequently Asked Questions
What is OCR and what does this tool do?
OCR (optical character recognition) converts the picture of text in a scanned PDF or photo into real, selectable characters. This tool runs OCR on each page of your PDF or image and gives you the extracted text to copy or download as a .txt file.
Is my file uploaded to a server?
No. The recognition happens 100% inside your browser, so your PDF or image never leaves your device. The only thing fetched from the network is the Tesseract language model (trained data), which is downloaded once and cached.
Which languages are supported?
Ten of the most common languages: English, Spanish, French, German, Portuguese, Italian, Hindi, Arabic, Chinese (Simplified), and Russian. Choose the language that matches your document before extracting for the best accuracy.
Can it read handwriting?
Not reliably. OCR is designed for printed and typed text. Handwriting, decorative fonts, very low-resolution scans, and skewed pages will produce poor or empty results โ this is a limit of OCR itself, not just this tool.
Does it work on images too, not just PDFs?
Yes. Alongside scanned PDFs you can drop a PNG or JPG image (such as a photo of a receipt, sign, or document) and extract the text from it the same way.
Is there a page or file-size limit?
There is no artificial page limit or signup. You can run multi-page PDFs; the only practical limit is your device's memory and how long you want to wait, since larger scans take longer to recognise.
How can I get the most accurate results?
Use a high-resolution scan (300 DPI or more), make sure the page is straight and well-lit, and select the correct document language. Clean, high-contrast black-on-white text recognises best.
How is this better than iLovePDF OCR or onlineocr.net?
Those tools upload your file to their servers and often gate languages, pages, or downloads behind signup or a paywall. This tool keeps your file private on your device, supports 10+ languages, works on both PDFs and images, and has no signup or page limit.