Image to Text
Extract text from images, screenshots and scans with OCR in your browser. Over 20 languages, nothing uploaded. Free and private.
Runs in your browser. Files never leave your device
About Image to Text
Turn a photo of a document, a screenshot or a scanned page into text you can copy, edit and search. Text recognition (OCR) runs right in your browser, in English and over 20 other languages, including Arabic, Chinese, Hindi and Japanese.
Your image never leaves your device. The recognition engine and English are downloaded from this site the first time you use the tool; other languages come from the jsDelivr CDN. All are cached for next time.
How to use Image to Text
- 1Add an image: drag and drop it, click to browse, or paste a screenshot.
- 2Choose the language of the text.
- 3Click Extract text, then copy or download the result.
Frequently asked questions
Is my image uploaded?
No. Text recognition runs on your device, in your browser. Neither the image nor the recognized text is sent anywhere.
How accurate is it?
Very good for clear, printed text such as documents and screenshots. Handwriting, unusual fonts, blur and low light reduce accuracy. Check the result and correct it in the text box before copying.
How do I get better results?
Use a sharp, well-lit image with the text the right way up, and choose the correct language. Cropping to just the text, and rotating sideways photos first, also helps.
Can it read PDFs?
Not directly. Convert the pages to images with PDF to JPG first, then extract the text from each image.
Why does the first run take longer?
The recognition engine (about 4 MB) and the language data (2–10 MB per language) are downloaded once and then cached by your browser, so later runs start quickly, even offline.