OCR in Any Language

JustScanText uses Tesseract.js which supports over 100 languages. Extract text from images in Spanish, Chinese, Japanese, Korean, Arabic, and many more - all processed privately in your browser.

How Language Support Works

Language models are downloaded on-demand when you first use them. Once loaded, they're cached in your browser for instant future use. The default English model is pre-loaded for fastest initial experience.

Popular Languages

Additional Languages

Tesseract.js supports 100+ languages including:

Arabic, Bengali, Bulgarian
Czech, Danish, Dutch
Finnish, Greek, Hebrew
Hungarian, Indonesian, Italian
Malay, Norwegian, Polish
Romanian, Swedish, Thai
Turkish, Ukrainian, Vietnamese
And many more...

Frequently Asked Questions

How do I change the OCR language?

Use the language selector in the tool before processing your images. The selected language model will be downloaded (if needed) and used for text extraction.

Can I OCR multiple languages in one image?

Tesseract works best with a single language per image. For mixed-language documents, try processing with each language separately, or use the language that appears most frequently in the image.

Why is non-English OCR slower the first time?

Language models need to be downloaded the first time you use them. After that, they're cached in your browser for instant access. English is pre-loaded by default.

Ready to extract text in any language?

Go to the OCR Scanner →