Azure AI Speech vs Cloudmersive OCR API

Azure AI Speech has no write-up on Specifiction yet; its figures are above.

Cloudmersive OCR API converts scanned documents and photos of documents or receipts into text using deep-learning OCR. It lists support for more than 90 languages, including English, simplified and traditional Chinese, French, Spanish, German, and Italian. For document and receipt photos, the API can locate the item and correct skew or rotation before recognition. Receipt extraction can return business name, address, phone number, total, and date. Image and photo endpoints offer Basic, Normal, and Advanced recognition modes; an OCR task may consume multiple API calls, including when processing a multipage PDF. The free tier costs nothing and includes 600 calls monthly, one call per second, and a 3.5 MB maximum file size. Using a free-tier key with OCR endpoints requires adding a credit card, and the free tier allows one simultaneous request. Paid plans start at $19.99 a month. Deployment options include public cloud, dedicated managed instances, private cloud, on-premises, PaaS, and government cloud. Cloudmersive says its stateless APIs do not retain payload data after a transaction and its endpoints use HTTPS with TLS 1.2 or later.