PDF OCR
Recognize text in scanned PDFs and images with on-device OCR, then copy or download it — private by design.
How to use the PDF OCR
-
Open a scanned PDF or image.
-
Run OCR and wait for recognition.
-
Copy the text or download it.
How to OCR a PDF
OCR (optical character recognition) reads text from images and scanned pages so you can copy, search or edit it. This tool renders pages with pdf.js and runs Tesseract OCR fully in your browser — the recognition engine and language data download to your device, so your documents are never uploaded.
Key features
- Recognize text in scans and images
- Copy text or download as .txt
- On-device engine — no upload
- Works on PDF pages and image files
Frequently asked questions
Is the OCR done on a server?
No. Recognition runs in your browser with Tesseract; the engine and language data load to your device.
Why is the first run slow?
The OCR engine and language data download once (several megabytes). After that, recognition is faster.
How accurate is it?
Accuracy depends on scan quality — clear, high-contrast pages give the best results.