019cd7ac-a157-7000-80af-a01e02656703 in this vapi the piece of audio after the agent stops talking at around this time is not picked up at all https://cdn.discordapp.com/attachments/1481391236836495442/1481391237150933073/Screenshot_2026-03-11_at_4.39.26_PM.png?ex=69b32499&is=69b1d319&hm=7707bda5fe5a68539337f9f43e1727caf3ddcaf5faa958383455dca065117988&

Try lowering your endpointing threshold to make user audio detection more responsive. For example, if you are using the Krisp provider, update your configuration as follows:

json
{
  "startSpeakingPlan": {
    "smartEndpointingPlan": {
      "provider": "krisp",
      "threshold": 0.5
    }
  }
}

This helps ensure the system picks up user speech right after the agent stops talking. See the [voice pipeline configuration documentation](https://docs.vapi.ai/customization/voice-pipeline-configuration) for more details. Source: - [Voice pipeline configuration](https://docs.vapi.ai/customization/voice-pipeline-configuration)