The Cloudmersive Optical Character Recognition API supports JSON, text, and XML formats when displaying image to text responses. API Key is required to authenticate. Cloudmersive provides scalable, computer vision and natural language APIs. Easily convert scanned documents, or photos of documents and receipts to digital text. Uses Machine Learning to automatically pre-process and then recognize the text across over 90 languages. Automatically unskews and unrotates images, and can automatically segment documents and receipts out of photographs.