### Answer This issue is likely related to how the turn-taking model determines when a user has finished speaking. [(1) ]() , [(2) ]() Here are a few things to try: 1. Check your first conversation node's instruction Make sure your initial node's prompt clearly instructs the agent on when to respond. If the instruction is ambiguous, the turn-taking model may wait for additional confirmation that the user is done speaking. 2. Consider using "Skip Response" on the first node If your first conversation node is purely for detection (IVR vs. person) and doesn't require the agent to speak, you can enable Skip Response in the node settings. When enabled, the transition will happen automatically after the agent finishes its task, without waiting for additional user input. [(3) ]() 3. Use a Static Sentence for immediate response On your second conversation node, you mentioned using a static sentence—this is good. The agent will say that fixed sentence first. However, ensure the transition from your first node is configured correctly so it moves promptly once a person is detected. 4. Review your transition conditions The transition from a conversation node happens "when user is done speaking." If your turn-taking model is interpreting the first "hello" as incomplete, it may be waiting for more input. Adjusting your node instruction to be more explicit about when to proceed could help. If the issue persists, it may be worth testing with a simpler flow to isolate whether the delay is in the detection logic or the transition configuration.

​ To learn more, see the sources I considered: [[1] VAD vs. Turn-Taking Endpoints in Conversational AI | Retell AI](https://www.retellai.com/blog/vad-vs-turn-taking-end-point-in-conversational-ai) [[2] Retell AI's Turn-Taking Model for Seamless Calls | Retell AI](https://www.retellai.com/blog/how-retell-ais-turn-taking-model-ensures-seamless-calls) [[3] Conversation Node](https://docs.retellai.com/build/conversation-flow/conversation-node) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.