CustomEndpointingModelSmartEndpointingPlan

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/CustomEndpointingModelSmartEndpointingPlan",
  "title": "CustomEndpointingModelSmartEndpointingPlan",
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "description": "This is the provider for the smart endpointing plan. Use `custom-endpointing-model` for custom endpointing providers that are not natively supported.",
      "enum": [
        "vapi",
        "livekit",
        "custom-endpointing-model"
      ],
      "example": "custom-endpointing-model"
    },
    "server": {
      "description": "This is where the endpointing request will be sent. If not provided, will be sent to `assistant.server`. If that does not exist either, will be sent to `org.server`.\n\nRequest Example:\n\nPOST https://{server.url}\nContent-Type: application/json\n\n{\n  \"message\": {\n    \"type\": \"call.endpointing.request\",\n    \"messages\": [\n      {\n        \"role\": \"user\",\n        \"message\": \"Hello, how are you?\",\n        \"time\": 1234567890,\n        \"secondsFromStart\": 0\n      }\n    ],\n    ...other metadata about the call...\n  }\n}\n\nResponse Expected:\n{\n  \"timeoutSeconds\": 0.5\n}\n\nThe timeout is the number of seconds to wait before considering the user's speech as finished. The endpointing timeout is automatically reset each time a new transcript is received (and another `call.endpointing.request` is sent).",
      "allOf": [
        {
          "$ref": "#/components/schemas/Server"
        }
      ]
    }
  },
  "required": [
    "provider"
  ]
}