Got a quick quesiton about custom llm integration. So from my understanding is that from your backend app the chat completion you return back the response content, however when executing the call I don't hear any thing returned back. Does anyone know if Vapi has a short keep alive for request to be given back the response? here's my chat completion request { "model": "gpt-4", "messages": [ {"role": "system", "content": "You are an assistant."}, {"role": "user", "content": "I dont have my passport or anything available?"} ] } and the response i get back from my backend { "id": "chatcmpl-1747484068", "object": "chat.completion", "created": 1747484068, "model": "gpt-4", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Could you please provide your full name and date of birth so I can verify your identity?" }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 0, "completion_tokens": 0, "total_tokens": 0 } } but its not producing the voice correctly back, I connected eleven labs and have all the apis keys etc connected Anyone else had this issue?