Hi all, I have a question regarding assistant overrides (https://vapi.ai/blog/debug-with-ease), I use it with

vapi.start()

while it's working for my custom llm, problem arises when I try switching to GPT realtime models, I think it's because some configuration is not supported there, e.g. it has limited voice selection, etc. But right now it just fails silently, is there a way to validate the override config first maybe? or perhaps it vapi.start should return error if a certain config is not supported?

Hey! To help track down this issue, could you share: \- The call ID \- When exactly this happened (the timestamp) \- What response you expected to get \- What response you actually got instead This would really help us figure out what went wrong!