### Answer Yes, you can configure your agent to leave a static message when voicemail is detected, which avoids using the LLM to generate a response dynamically (and thus reduces token usage) . [(1) ]() Here's how to set it up: 1. Enable Voicemail Detection in your agent settings under Call Settings. 2. Choose Leave a message as the voicemail behavior. 3. Select Static message — the agent will leave a pre-recorded message like

Hi, this is {{your name}}, please give us a callback tomorrow at 10am.

This static message option means the agent speaks a fixed message rather than generating one via the LLM, which should help minimize token and call costs when hitting voicemail. You can also configure this via the API using the

voicemail_option

field with `type: "static_text"`: [(2) ]()

json
"voicemail_option": {
  "action": {
    "type": "static_text",
    "text": "Please give us a callback tomorrow at 10am."
  }
}

Dynamic variables are supported in the static message as well. [(1) ]()

​ To learn more, see the sources I considered: [[1] Handle voicemail](https://docs.retellai.com/build/handle-voicemail) [[2] Create Voice Agent](https://docs.retellai.com/api-references/create-agent) ​

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

### Answer The available documentation doesn't explicitly detail the exact cost breakdown for static voicemail messages versus LLM-generated messages. [(1) ]() What the documentation does confirm: - Using a static message means the agent leaves a pre-recorded message rather than generating one dynamically via the LLM. - The prompt option generates a message dynamically based on instructions you provide. The static message approach should reduce LLM token usage since no generation occurs, but the documentation doesn't specify whether there are additional TTS (text-to-speech) costs or other charges for the voicemail portion of the call. For specific cost clarification, I'd recommend reaching out to support: - Visit [Contact Sales]() - Check out [) Would you like me to try to provide a general answer based on typical voice AI pricing models?

​ To learn more, see the sources I considered: [[1] Handle voicemail](https://docs.retellai.com/build/handle-voicemail) ​

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