config.json

{
  "model_type": "style_bert_vits2",
  "language": "ja",
  "sample_rate": 44100,
  "n_speakers": 4,
  "speakers": [
    {
      "id": 0,
      "name": "Default",
      "gender": "neutral",
      "description": "デフォルト話者"
    },
    {
      "id": 1,
      "name": "Female1",
      "gender": "female",
      "description": "女性話者1"
    },
    {
      "id": 2,
      "name": "Male1", 
      "gender": "male",
      "description": "男性話者1"
    },
    {
      "id": 3,
      "name": "Child1",
      "gender": "neutral",
      "description": "子供話者1"
    }
  ],
  "emotions": [
    "neutral",
    "happy",
    "sad", 
    "angry",
    "surprised",
    "fear",
    "disgust"
  ],
  "inference_params": {
    "speed": {
      "min": 0.5,
      "max": 2.0,
      "default": 1.0
    },
    "pitch": {
      "min": -12.0,
      "max": 12.0,
      "default": 0.0
    },
    "intonation": {
      "min": 0.0,
      "max": 2.0,
      "default": 1.0
    },
    "volume": {
      "min": 0.0,
      "max": 2.0,
      "default": 1.0
    }
  },
  "max_text_length": 500,
  "supported_formats": ["wav", "mp3"],
  "version": "2.0"
}