Hi everyone, I'm trying to build an overflow handling assistant and I need help with Warm Transfer Experimental. What I'm trying to achieve: My assistant (Sienna) answers inbound calls, identifies the department, and transfers the call. If the department doesn't pick up within 15 seconds, I need the call to return back to Sienna automatically so she can take the caller's details. The whole thing needs to happen in one single call so the assistant retains the context of the conversation. What I've done: Transfer mode set to Warm Transfer Experimental on all destinations End call if transfer fails is unchecked Summary generation disabled What's happening: The transfer fires correctly but after 15 seconds of no answer the call does not return back to the assistant. The call just dies. My question: Is Warm Transfer Experimental the right mode for this use case? And if so what exact settings are needed to make the call return to the assistant when no one answers? Has anyone successfully built this and can share their setup?

Warm Transfer Experimental does not support returning the call to your assistant if the transfer fails—use Assistant-based warm transfer instead. Here’s a sample configuration to achieve overflow handling (return to Sienna if no answer in 15 seconds):

json
{
  "type": "transferCall",
  "destinations": [
    {
      "type": "number",
      "number": "+1234567890",
      "transferPlan": {
        "mode": "warm-transfer-experimental",
        "transferAssistant": {
          "firstMessage": "Hi, I have a customer for you.",
          "maxDurationSeconds": 15,
          "model": { "provider": "openai", "model": "gpt-4o" }
        }
      }
    }
  ]
}

Switch to assistant-based warm transfer and set

maxDurationSeconds

to 15; the call will return to Sienna if unanswered, preserving context. See [Assistant-based warm transfer documentation](https://docs.vapi.ai/calls/assistant-based-warm-transfer) for details. Source: - [Assistant-based warm transfer documentation](https://docs.vapi.ai/calls/assistant-based-warm-transfer)

Update — tried the assistant-based warm transfer config I updated the tool via the API with the transferAssistant block and maxDurationSeconds set to 15. The good news is the call is now returning to Sienna after no answer which is working perfectly. The only remaining issue is VAPI is saying "could not transfer the call" before Sienna continues. I removed the fallbackPlan completely from the JSON but it's still saying it — seems like VAPI is hardcoding that message internally. Is there any way to suppress that message completely so Sienna just continues the conversation naturally without that message playing?

Can you please share the call id where you're facing the issue, so we can investigate more