mulri requesst & bug with voice chnage

[habibaezz01]

Hi, thanks for the great work on this model!

I had two questions:

Concurrent/Async Request Handling:
Is there any plan or recommended approach to support multiple concurrent inference requests efficiently? Specifically, is there any guidance on integrating something like vLLM or another async-compatible backend to allow better scalability?

Voice Change Issue:
I've noticed that the voice output sometimes changes unexpectedly, even with the same input settings.