Image to Word (OCR)
Read text from images and scanned PDFs with OCR, in English or Hindi, and download it as Word or plain text.
Runs in your browser. Your input is processed on your device and is not uploaded to our server.
Drop images or a scanned PDFJPG, PNG, WebP or PDF, up to 50 MB. Processed on your device.
OCR makes mistakes. Proofread the text, especially names, numbers and dates.
How to use the Image to Word (OCR)
- Drop images or a scanned PDF.
- Choose the language of the text.
- Check and correct the text, then download the DOCX or TXT.
Recognition uses Tesseract, a widely used open-source OCR engine, running on your device. The first run downloads about 5–10 MB of engine files from this site, and your document stays in your browser.
Accuracy depends on the source: sharp, straight, printed text works well; handwriting, photos at an angle, low resolution and unusual fonts do not. The tool shows the engine’s confidence, and the text is plain, without the original layout. Always proofread it.
Frequently asked questions
Which languages are supported?
English, Hindi, and the two together.
Does it read handwriting?
Not reliably. Tesseract is designed for printed text.
Why is it slow?
Recognition runs on your device. Pages take from a few seconds to a minute, depending on your device and the image size.