Extract text from any document — हिंदी और English
Upload photos, scans, PDFs or Office files. Lipi OCR reads Hindi, English and 100+ other languages using open-source engines, and gives you editable text.
How it works
1 · Upload
Images, scanned or digital PDFs, Word/LibreOffice/PowerPoint/Excel files.
2 · Recognise
Digital PDFs keep their exact text. Scanned pages and images are read by Tesseract or EasyOCR.
3 · Copy or download
Edit the result in the browser, copy it, or download as .txt / .json.
🔒 Uploaded files are deleted from the server as soon as processing finishes; extracted text is kept in memory for 1 hour so you can download it, then discarded.