Speech-to-Text API for foreign languages

I want to integrate speech-to-text into a piece of software I am working on. What recommendations are there for software that will convert foreign language, such as Mandarin, into text. Preferably, it will perform text to speech and include the pinyin (with tones). Is there any such software?

The Google Translate web platform works perfectly, but their API doesn't seem to offer any endpoints that I can integrate with my software (even with a purchased Google API key).

SayHiTranslate offers a nifty iOS app, but again, no API endpoints that I can integrate.

This CNET article mentions several other options, such as Bing and Skype, but all are services and apps with no integration capabilities.

Any recommendations or ideas would be helpful.