OCR for the documents that are hard to read.
Runemic OCR reads Arabic, Persian, Urdu, Hindi, Chinese and Japanese pages, old scans and handwriting, in reading order. Free to try, no account.
Click a page to watch Runemic read it.
Receipts, letters, books, forms and archives.
Rune-1 models
Multilingual OCR for difficult documents. Reads the text, the layout and the basic structure of a page, across many scripts and languages.
Model card
Scan to PDF
Take a picture of a page or drop photos: the page is found, straightened and flattened, and you get a PDF, free and without an account. It can read the text too.
Products
Digitization
We digitize collections of books, letters and other documents: we scan them, run OCR and return searchable files and structured data.
ServicesRead pages from your own code
One HTTP request per page, the text back as Markdown. Sign in with GitHub or Hugging Face to get an API key.
- Sign in for 2,500 free credits, no card needed
- Compare up to three models, and get an API key with cURL, Python and JavaScript examples
# one page in, Markdown out curl https://api.runemic.com/v1/ocr \ -H "Authorization: Bearer $RUNEMIC_KEY" \ -F "file=@page.png" # → { "text": "# Invoice No. 4821 …", "usage": { "credits_used": 2 } }