Free OCR Scanner — Extract Text from Images & PDFs
Extract text from images, PDFs, TIFF, and scans with OCR. Supports English, Nepali (नेपाली), and Hindi (हिन्दी), and can produce a searchable PDF. 100% client-side, no uploads.
How to Extract Text with OCR
Upload an image, PDF, TIFF, or scan. Choose your language — English, Nepali, Hindi, or bilingual — and click Scan. The text is extracted and shown instantly.
Download the result as TXT, Word (.docx), or JSON, or create a Searchable PDF that keeps the original document with a hidden text layer.
- Upload an image, PDF, TIFF, or scan
- Choose English, Nepali, Hindi, or bilingual
- Click Scan and review the extracted text
- Download as TXT, Word, JSON, or a Searchable PDF
Nepali & Hindi OCR (Devanagari)
Nepali and Hindi share the same Devanagari script, so a single Devanagari-trained model accurately recognizes both languages. Perfect for scanned documents, books, and forms in Nepal and India.
Frequently Asked Questions
Does the OCR tool support Nepali and Hindi text?
Yes — it supports English, Nepali (नेपाली), Hindi (हिन्दी), and bilingual modes. Since Nepali and Hindi share the Devanagari script, one model recognizes both accurately.
Can I get a searchable PDF of my scanned document?
Yes — choose the Searchable PDF (.pdf) download option. It keeps the original document and adds an invisible OCR text layer so you can search and copy text.
Is the OCR free and private?
Yes — it's free and 100% client-side. Documents are processed in your browser with Tesseract.js and never uploaded.