{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://jambonz.org/schema/verbs/config",
  "minVersion": "0.9.6",
  "title": "Config",
  "description": "Sets session-level defaults for the call. Configures default TTS, STT, VAD, recording, streaming, and other session-wide settings. These defaults apply to all subsequent verbs unless overridden at the verb level. Typically the first verb in an application. Can be used multiple times during a call to change settings.",
  "type": "object",
  "properties": {
    "verb": {
      "const": "config",
      "description": "The verb name."
    },
    "id": {
      "type": "string",
      "description": "An optional unique identifier for this verb instance."
    },
    "synthesizer": {
      "$ref": "../components/synthesizer",
      "description": "Default TTS configuration for the session."
    },
    "recognizer": {
      "$ref": "../components/recognizer",
      "description": "Default STT configuration for the session."
    },
    "bargeIn": {
      "type": "object",
      "description": "Default barge-in configuration. When enabled, callers can interrupt playing prompts with speech or DTMF.",
      "properties": {
        "enable": {
          "type": "boolean"
        },
        "sticky": {
          "type": "boolean",
          "description": "If true, barge-in settings persist across verbs rather than resetting after each verb."
        },
        "actionHook": {
          "$ref": "../components/actionHook"
        },
        "input": {
          "type": "array",
          "items": {
            "type": "string",
            "enum": [
              "speech",
              "digits"
            ]
          }
        },
        "minBargeinWordCount": {
          "type": "number"
        }
      }
    },
    "ttsStream": {
      "type": "object",
      "description": "Default TTS streaming configuration for the session.",
      "properties": {
        "enable": {
          "type": "boolean"
        },
        "synthesizer": {
          "$ref": "../components/synthesizer"
        }
      }
    },
    "record": {
      "type": "object",
      "description": "Session-level call recording configuration.",
      "additionalProperties": true
    },
    "listen": {
      "type": "object",
      "description": "Session-level audio streaming configuration defaults. Properties match the listen verb but no fields are required here.",
      "additionalProperties": true
    },
    "stream": {
      "type": "object",
      "description": "Session-level audio streaming configuration defaults. Alias for 'listen'.",
      "additionalProperties": true
    },
    "transcribe": {
      "type": "object",
      "description": "Session-level transcription configuration defaults.",
      "additionalProperties": true
    },
    "amd": {
      "$ref": "../components/amd",
      "description": "Session-level answering machine detection configuration."
    },
    "fillerNoise": {
      "$ref": "../components/fillerNoise",
      "description": "Default filler noise configuration for the session."
    },
    "vad": {
      "$ref": "../components/vad",
      "description": "Default voice activity detection configuration for the session."
    },
    "notifyEvents": {
      "type": "boolean",
      "description": "If true, send call events (e.g. DTMF, call status changes) to the application via the status webhook."
    },
    "notifySttLatency": {
      "type": "boolean",
      "description": "If true, include STT latency measurements in webhook payloads."
    },
    "reset": {
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "Reset specific session-level settings to their defaults. Pass a setting name or array of setting names to reset."
    },
    "onHoldMusic": {
      "type": "string",
      "format": "uri",
      "description": "URL of an audio file to play when the call is placed on hold."
    },
    "actionHookDelayAction": {
      "$ref": "../components/actionHookDelayAction",
      "description": "Default configuration for handling slow webhook responses."
    },
    "sipRequestWithinDialogHook": {
      "$ref": "../components/actionHook",
      "description": "A webhook to invoke when a SIP request (e.g. INFO, NOTIFY) is received within the dialog."
    },
    "boostAudioSignal": {
      "oneOf": [
        {
          "type": "number"
        },
        {
          "type": "string"
        }
      ],
      "description": "Boost (or attenuate) the audio signal in dB for the session."
    },
    "referHook": {
      "$ref": "../components/actionHook",
      "description": "A webhook to invoke when a SIP REFER request is received."
    },
    "earlyMedia": {
      "type": "boolean",
      "description": "If true, allow early media (audio before call answer) for the session."
    },
    "autoStreamTts": {
      "type": "boolean",
      "description": "If true, automatically use streaming TTS for all 'say' verbs in the session."
    },
    "disableTtsCache": {
      "type": "boolean",
      "description": "If true, disable TTS caching for the session."
    },
    "trackTtsPlayout": {
      "type": "boolean",
      "description": "If true, report the actual text spoken via TTS. Requires a TTS vendor that supports alignment data (e.g. ElevenLabs). On each utterance completion or interruption, a tts_spoken event is sent to the '/streaming-event' endpoint with fields: 'text' (string — the text actually spoken) and 'bargein' (boolean — true if the user interrupted before TTS finished). See the tts-streaming-event callback schema for full details."
    },
    "noiseIsolation": {
      "type": "object",
      "description": "Noise isolation configuration to reduce background noise on call audio. Defaults to filtering inbound (caller) audio; can also filter outbound audio via the direction option.",
      "properties": {
        "enable": {
          "type": "boolean"
        },
        "vendor": {
          "type": "string"
        },
        "level": {
          "type": "number"
        },
        "model": {
          "type": "string"
        },
        "label": {
          "type": "string",
          "description": "Label of the speech credential to use, for vendors that need one (kugelaudio)."
        },
        "auth": {
          "type": "object",
          "description": "Optional inline credentials for vendors that need them (kugelaudio). When omitted, feature-server looks up the speech credential by (vendor, label).",
          "properties": {
            "apiKey": {
              "type": "string"
            },
            "apiUri": {
              "type": "string",
              "description": "Vendor API host, e.g. api.eu.kugelaudio.com."
            }
          },
          "additionalProperties": true
        }
      }
    },
    "turnTaking": {
      "type": "object",
      "description": "Turn-taking detection configuration for conversational AI applications.",
      "properties": {
        "enable": {
          "type": "boolean"
        },
        "vendor": {
          "type": "string"
        },
        "threshold": {
          "type": "number"
        },
        "model": {
          "type": "string"
        }
      }
    }
  },
  "required": [],
  "examples": [
    {
      "verb": "config",
      "synthesizer": {
        "vendor": "elevenlabs",
        "voice": "Rachel",
        "language": "en-US"
      },
      "recognizer": {
        "vendor": "deepgram",
        "language": "en-US"
      },
      "fillerNoise": {
        "enable": true,
        "url": "https://example.com/sounds/typing.wav",
        "startDelaySecs": 2
      }
    }
  ]
}