Document and OCR tools
Nepali OCR
Turn photos and scans of printed Nepali and English into text you can edit, copy and download.
1. Choose an image or PDF
JPG, PNG, WebP or PDF, up to 25 MB. The file stays on your device.
Privacy and limits
Private by design. Recognition runs in your browser with the open-source Tesseract engine. Your images and PDFs are never uploaded; only the OCR engine and language models are downloaded from this site.
- Printed text works best. Clear, straight scans of typed Nepali (Unicode fonts and most Preeti-style prints) and English read well.
- Handwriting is not supported. Handwritten Nepali or English usually comes out wrong or empty.
- Low-quality images cause errors. Blurry, dark, skewed or low-resolution photos, stamps, watermarks and coloured backgrounds reduce accuracy. Half-letters and conjuncts (संयुक्त अक्षर) are the most common mistakes.
- Tables and columns lose their layout. Text is returned line by line.
- Always proofread names, numbers and dates, especially for official documents.
How to use
- 1Choose a JPG, PNG, WebP or PDF file. It opens on your device and is not uploaded.
- 2Rotate the page until the text is upright, and crop to the text you need.
- 3Choose the language in the document and tap Extract text.
- 4Correct any mistakes in the text box, then copy it or download it as a TXT file.