Good day. We try to build an app based on the speech recognition model.
Most important requirements are:
* Using RingCentral SDK (no any GUI app is allowed)
* Real-time (by exposing Supervisor feature)
* Use both audio channels
* Processing in parallel all inbound/outbound calls at the same time

We went through https://support.ringcentral.com/s/article/Supervisor-Functions-Limitations-RingCentral-Contact-Center?language=en_US
But it's not fully covered our concern. May you please shad light a bit, and explain does the RingCentral Supervisor feature is good enough to implement our app following all the requirements above? Thank you in advance.