audioVerboseResponse

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/nielseniq/main/json-schema/nielseniq-audio-verbose-response-schema.json",
  "title": "audioVerboseResponse",
  "description": "Translation or transcription response when response_format was verbose_json",
  "x-generated": "2026-10-18",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/nielseniq-docusearch-us-azure-openai-service-api-openapi.yml#/components/schemas/audioVerboseResponse",
  "required": [
    "text"
  ],
  "type": "object",
  "allOf": [
    {
      "$ref": "#/$defs/audioResponse"
    },
    {
      "properties": {
        "task": {
          "enum": [
            "transcribe",
            "translate"
          ],
          "type": "string",
          "description": "Type of audio task.",
          "x-ms-enum": {
            "modelAsString": true
          }
        },
        "language": {
          "type": "string",
          "description": "Language."
        },
        "duration": {
          "type": "number",
          "description": "Duration."
        },
        "segments": {
          "type": "array",
          "items": {
            "$ref": "#/$defs/audioSegment"
          }
        }
      }
    }
  ],
  "$defs": {
    "audioResponse": {
      "required": [
        "text"
      ],
      "type": "object",
      "properties": {
        "text": {
          "type": "string",
          "description": "Translated or transcribed text."
        }
      },
      "description": "Translation or transcription response when response_format was json"
    },
    "audioSegment": {
      "type": "object",
      "properties": {
        "id": {
          "type": "integer",
          "description": "Segment identifier."
        },
        "seek": {
          "type": "number",
          "description": "Offset of the segment."
        },
        "start": {
          "type": "number",
          "description": "Segment start offset."
        },
        "end": {
          "type": "number",
          "description": "Segment end offset."
        },
        "text": {
          "type": "string",
          "description": "Segment text."
        },
        "tokens": {
          "type": "array",
          "items": {
            "type": "number"
          },
          "description": "Tokens of the text."
        },
        "temperature": {
          "type": "number",
          "description": "Temperature."
        },
        "avg_logprob": {
          "type": "number",
          "description": "Average log probability."
        },
        "compression_ratio": {
          "type": "number",
          "description": "Compression ratio."
        },
        "no_speech_prob": {
          "type": "number",
          "description": "Probability of 'no speech'."
        }
      },
      "description": "Transcription or translation segment."
    }
  }
}