### Answer I don't have detailed documentation on a specific setting called "Dynamically adjust based on user input" for responsiveness. Here's what I can tell you about responsiveness in Retell AI: Responsiveness setting controls how responsive the agent is. [(1) ]() Setting it lower makes the agent respond slower, which can be useful when talking to folks like elderly. Reducing responsiveness by 0.1 adds 0.5 seconds of agent wait time. Dynamic adjustment during a call is available via the LLM WebSocket. You can send an "update_agent" event to modify

responsiveness

mid-call: [(2) ]()

json
{
  "response_type": "update_agent",
  "agent_config": {
    "responsiveness": 0.8
  }
}

The

responsiveness

value ranges from 0 to 1—lower values mean a less responsive agent (waits more, responds slower) , while higher values mean faster exchanges. There's also a feature request on the roadmap for dynamically adjusting responsiveness and voice speed during sessions. [(3) ]() If you're seeing a specific UI option labeled "Dynamically adjust based on user input," I don't have documentation on exactly how that automatic adjustment works. You may want to check the dashboard for tooltips or reach out via the support channels for clarification.

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

​ To learn more, see the sources I considered: [[1] Step 1: Configure global settings](https://docs.retellai.com/build/conversation-flow/global-setting) [[2] LLM WebSocket](https://docs.retellai.com/api-references/llm-websocket) [[3] Dynamically adjust responsiveness, voice speed during session](https://community.retellai.com/t/dynamically-adjust-responsiveness-voice-speed-during-session/683) ​