Call id: f7b093bf-7ad0-4de5-b96f-1ec3a7654d8e I would expect the assistant to continue talking when the tool call returns the open slots in the calendar. The assistant only starts telling me about the open slots once I speak again. Am I suppose to do something in the prompt to achieve this or change the success message. Otherwise everything works fine. In short, what do I need to do to get the assistant to continue talking after the tool call finished? https://cdn.discordapp.com/attachments/1268401062738399283/1268401063040385044/message.txt?ex=66ac4a0b&is=66aaf88b&hm=786a7951aa4a7ddbf9f5604d9b3fa0329349617bb63960d5bbc6c6d8d7238343&

@Quintus It sounds like you're experiencing an issue where the assistant waits for your input before providing information on the open slots in the calendar after a tool call. To address this, you may need to adjust the behavior of the assistant to ensure it speaks first and provides the information immediately after the tool call is completed. If you're using a specific API or function that controls the assistant's behavior, you might need to set a parameter that controls the assistant's initiative to speak first. For example, if there's a parameter that determines whether the assistant waits for the user to speak or if it should provide information proactively, you should set it accordingly. In the context of VAPI, if there's an option like

assistant-speaks-first

, you should enable it to ensure the assistant provides the information without waiting for user input. If you're not sure how to set this or if such an option exists, please ask support for more info on this. If you have access to the code or settings of the assistant, look for a setting related to speech initiation or conversation flow control and adjust it to make the assistant more proactive. If you need further assistance with this issue, please provide more details or context, and I'll do my best to help you resolve it.

remove the request-complete message it will speak the results as per your instructions.

json
      "messages": [
        {
          "content": "Please wait...",
          "type": "request-start"
        },
        {"content": "Got it.", "type": "request-complete"},
        {
          "content": "I couldn't get the open slots right now.",
          "type": "request-failed"
        },
        {
          "content": "It appears there is some delay in getting the open slots.",
          "type": "request-response-delayed",
          "timingMilliseconds": 5000
        }
      ]

Hi, I'm using the UX dashboard not the API, and for Knowledge tool calls there is no such option to state if to respond or not