Image & Scanned PDF to Text (OCR)
Extract text from many photos and scanned PDFs, in English or Hindi.
âšī¸ First use downloads the OCR engine and language data (about 6 MB, English â 3 MB, Hindi â 1.4 MB) once, then it is cached. Everything runs on your device, so it is slower on phones and for big PDFs.
Advanced settings
How to use Image & Scanned PDF to Text (OCR)
Recognise text in photos, screenshots and scanned PDFs and save it as plain .txt files. Add many files at once and download all text as a ZIP. Accuracy is best on sharp, straight, high-contrast scans; handwriting and low-quality photos give poor results.
- Add images or scanned PDFs.
- Choose the language (English, Hindi, or both).
- Process, then download each .txt or everything as a ZIP.
FAQ
Is my document uploaded for text recognition?
No. The OCR engine and language data are downloaded to your browser once and run on your device. Your images and PDFs are never sent anywhere.
Why is the first run slow?
The OCR engine and language data download once. Later runs start much faster. Large scanned PDFs take time because every page is recognised on your own device.
Can it read handwriting?
Not reliably. It is built for printed text.