Hi everyone!
First of all, I'm not even a beginner on any Cisco tech, so what I'm asking might not be possible.
I wanted to know if there's any way to configure something like a voice audio middleware that could let us:
- Capture the incoming/outgoing audio stream during a conversation
- Process said stream consuming an external Web API
- Return the new processed stream.
For example, I could want to transform the human voice to a bot voice using an external service like Azure speech (not a real use case, but helps to explain).
Is there any way to do this? I'm playing with UCCX sandbox, and so far i managed to do this locally on each PC using an app that creates its own I/O audio devices, and setting this devices into Jabber configuration, but I would like to avoid having to configure each PC, and it wouldn't work on the case of a desk phone.
The environment that I'm playing with is UCCX 11.5 (the sandbox) and a 7841 desk phone.
Thanks!
