Live API Audio to Audio tool grounding

I am using the new gemini 2.0 live API, and using Audio to Audio. I’m noticing that when I return information from a function call the model doesn’t seem to see that information. I was reading that this is an async operation, is there a way to force the live api to wait to generate it’s next audio response until the tool call is complete?

@Zachary_Lee

Could you share the code you’re using?