Hey all I'm using the flex mode on a multi-prompt. I have an end call node that is supposed to speak on execution, but it never does. I was wondering if there's any way to get this to happen? The calls end pretty abruptly without any goodbye.

have it output the response before it ends the call

I was struggling with this issue as well, but I found a fix! Hopefully it works for you too. I fixed it by moving the logic from the Node to the Global Prompt. In Flex Mode, a 'race condition' often causes the tool to terminate the call before the TTS finishes I believe. Instead of using 'Speak during execution' in the node, I left the node empty and added a strict 'Output-First' protocol to the Global Prompt: - Instruction: Explicitly tell the agent to output the farewell sentence (e.g., 'Have a great day') first. - Sequential Action: Instruct the agent to trigger the end_call tool immediately after generating that specific sentence. - No Wait: Command the agent to never wait for user input between the speech and the tool call. I believe this forces the LLM to sequence the speech and the hangup technical action correctly every time. Good luck!