Dear I'm using a function tool but the response is not working if I'm using the mode "gpt-4o-realtime-preview-2024-12-17" of "openai" provider but if I've changed it to gpt-4o the response works. Could you guys please have a quick fix for that? @Shubham Bajaj @jordan @0xBLURRYFΛCE @AiTitus :)

The

gpt-4o-realtime-preview-2024-12-17

model is in beta and has known issues with webhook response parsing. Switch to the standard

gpt-4o

model for production use as recommended by OpenAI. If you must use the realtime model for testing, ensure your webhook response follows this exact format:

json
{
    "results": [
        {
            "toolCallId": "call_id",
            "result": "Your result here"
        }
    ]
}

Sources: - [Discord message about webhook response issues](https://discord.com/channels/1211482211119796234/1334547175253868725) - [Discord message about model stability](https://discord.com/channels/1211482211119796234/1337465970557452299) - [Vapi documentation on OpenAI Realtime](https://docs.vapi.ai/openai-realtime)

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!