{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/sakura-internet/main/json-schema/sakura-internet-tts-synthesis-request-schema.json",
  "title": "TtsSynthesisRequest",
  "x-generated": "2026-10-09",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/sakura-internet-ai-engine-inference-openapi.yml#/components/schemas/TtsSynthesisRequest",
  "type": "object",
  "required": [
    "accent_phrases",
    "speedScale",
    "pitchScale",
    "intonationScale",
    "volumeScale",
    "prePhonemeLength",
    "postPhonemeLength",
    "outputSamplingRate",
    "outputStereo",
    "kana"
  ],
  "additionalProperties": true,
  "properties": {
    "accent_phrases": {
      "type": "array",
      "description": "アクセント句のリスト",
      "items": {
        "type": "object",
        "description": "Accent Phrase",
        "additionalProperties": true
      }
    },
    "speedScale": {
      "type": "number",
      "description": "全体の話速"
    },
    "pitchScale": {
      "type": "number",
      "description": "全体の音高"
    },
    "intonationScale": {
      "type": "number",
      "description": "全体の抑揚"
    },
    "volumeScale": {
      "type": "number",
      "description": "全体の音量"
    },
    "prePhonemeLength": {
      "type": "number",
      "description": "音声の前の無音時間"
    },
    "postPhonemeLength": {
      "type": "number",
      "description": "音声の後の無音時間"
    },
    "pauseLength": {
      "description": "句読点などの無音時間。nullのときは無視される。デフォルト値はnull\n",
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ]
    },
    "pauseLengthScale": {
      "type": "number",
      "description": "句読点などの無音時間（倍率）。デフォルト値は1",
      "default": 1
    },
    "outputSamplingRate": {
      "type": "integer",
      "description": "音声データの出力サンプリングレート"
    },
    "outputStereo": {
      "type": "boolean",
      "description": "音声データをステレオ出力するか否か"
    },
    "kana": {
      "type": "string",
      "description": "読み（かな）。\n[読み取り専用] AquesTalk風記法によるテキスト。音声合成用のクエリとしては無視される\n"
    }
  }
}