diodiogod-TTS-Audio-Suite/utils/audio_cpp/model_specs/index_tts2.json

{
  "family": "index_tts2",
  "display_name": "IndexTTS2",
  "description": "Zero-shot TTS system for Chinese and English speech synthesis with voice cloning, emotion-speaker decoupling, text or audio emotion control, and explicit duration control.",
  "category": "tts",
  "status": "supported",
  "tasks": [
    "tts",
    "clone"
  ],
  "modes": [
    "offline"
  ],
  "languages": [
    "zh",
    "en"
  ],
  "capabilities": {
    "tts": [
      "emotion_control"
    ],
    "clone": [
      "speaker_reference",
      "emotion_control"
    ]
  },
  "runtime": {
    "tags": [
      "gguf"
    ]
  },
  "ui": {
    "recommended_package": "index_tts2_q8_0",
    "tags": [
      "TTS",
      "Clone",
      "GGUF"
    ],
    "docs": [
      "docs/tts.md",
      "docs/gguf.md"
    ]
  },
  "package_defaults": {
    "download": {
      "kind": "huggingface_snapshot",
      "repo": "audio-cpp/audio.cpp-gguf",
      "revision": "main",
      "gated": false
    }
  },
  "packages": [
    {
      "id": "index_tts2_q8_0",
      "display_name": "IndexTTS2 Q8_0 GGUF",
      "default": true,
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "IndexTTS2-GGUF",
      "files": [
        "IndexTTS2-GGUF/index-tts2-q8_0.gguf"
      ],
      "strip_prefix": "IndexTTS2-GGUF"
    },
    {
      "id": "index_tts2_f16",
      "display_name": "IndexTTS2 F16 GGUF",
      "format": "gguf",
      "precision": "f16",
      "target_directory": "IndexTTS2-GGUF",
      "files": [
        "IndexTTS2-GGUF/index-tts2-f16.gguf"
      ],
      "strip_prefix": "IndexTTS2-GGUF"
    },
    {
      "id": "index_tts2_orig",
      "display_name": "IndexTTS2 Original-Dtype GGUF",
      "format": "gguf",
      "precision": "orig",
      "target_directory": "IndexTTS2-GGUF",
      "files": [
        "IndexTTS2-GGUF/index-tts2-orig.gguf"
      ],
      "strip_prefix": "IndexTTS2-GGUF"
    },
    {
      "id": "index_tts2_safetensors",
      "display_name": "IndexTTS2 Safetensors",
      "format": "safetensors",
      "precision": "native",
      "target_directory": "IndexTTS-2",
      "files": [
        "config.yaml",
        "bpe.model",
        "gpt.safetensors"
      ],
      "download": {
        "kind": "huggingface_snapshot",
        "repo": "mlx-community/index-tts2-mlx"
      }
    }
  ],
  "sources": [
    {
      "format": "gguf",
      "roots": {
        "model": ".",
        "weights": "$gguf"
      },
      "files": {
        "config": "model:config.yaml",
        "bpe": "model:bpe.model",
        "wav2vec2bert_config": "model:w2v-bert-2.0/config.json",
        "wav2vec2bert_preprocessor_config": "model:w2v-bert-2.0/preprocessor_config.json",
        "bigvgan_config": "model:bigvgan/config.json",
        "qwen_emotion_config": "model:qwen0.6bemo4-merge/config.json",
        "qwen_emotion_generation_config": "model:qwen0.6bemo4-merge/generation_config.json",
        "qwen_emotion_tokenizer": "model:qwen0.6bemo4-merge/tokenizer.json",
        "qwen_emotion_tokenizer_config": "model:qwen0.6bemo4-merge/tokenizer_config.json",
        "qwen_emotion_vocab": "model:qwen0.6bemo4-merge/vocab.json",
        "qwen_emotion_merges": "model:qwen0.6bemo4-merge/merges.txt"
      },
      "tensors": {
        "gpt": {
          "source": "weights:",
          "prefix": "gpt"
        },
        "s2mel": {
          "source": "weights:",
          "prefix": "s2mel"
        },
        "speaker_matrix": {
          "source": "weights:",
          "prefix": "speaker_matrix"
        },
        "emotion_matrix": {
          "source": "weights:",
          "prefix": "emotion_matrix"
        },
        "wav2vec2bert_stats": {
          "source": "weights:",
          "prefix": "wav2vec2bert_stats"
        },
        "wav2vec2bert": {
          "source": "weights:",
          "prefix": "wav2vec2bert"
        },
        "semantic_codec": {
          "source": "weights:",
          "prefix": "semantic_codec"
        },
        "campplus": {
          "source": "weights:",
          "prefix": "campplus"
        },
        "bigvgan": {
          "source": "weights:",
          "prefix": "bigvgan"
        },
        "qwen_emotion": {
          "source": "weights:",
          "prefix": "qwen_emotion"
        }
      }
    },
    {
      "format": "safetensors",
      "roots": {
        "model": "."
      },
      "files": {
        "config": "model:config.yaml",
        "bpe": "model:bpe.model",
        "wav2vec2bert_config": "model:w2v-bert-2.0/config.json",
        "wav2vec2bert_preprocessor_config": "model:w2v-bert-2.0/preprocessor_config.json",
        "bigvgan_config": "model:bigvgan/config.json",
        "qwen_emotion_config": "model:qwen0.6bemo4-merge/config.json",
        "qwen_emotion_generation_config": "model:qwen0.6bemo4-merge/generation_config.json",
        "qwen_emotion_tokenizer": "model:qwen0.6bemo4-merge/tokenizer.json",
        "qwen_emotion_tokenizer_config": "model:qwen0.6bemo4-merge/tokenizer_config.json",
        "qwen_emotion_vocab": "model:qwen0.6bemo4-merge/vocab.json",
        "qwen_emotion_merges": "model:qwen0.6bemo4-merge/merges.txt"
      },
      "tensors": {
        "gpt": "model:gpt.safetensors",
        "s2mel": "model:s2mel.safetensors",
        "speaker_matrix": "model:feat1.safetensors",
        "emotion_matrix": "model:feat2.safetensors",
        "wav2vec2bert_stats": "model:wav2vec2bert_stats.safetensors",
        "wav2vec2bert": "model:w2v-bert-2.0/model.safetensors",
        "semantic_codec": "model:semantic_codec_model.safetensors",
        "campplus": "model:campplus.safetensors",
        "bigvgan": "model:bigvgan/model.safetensors",
        "qwen_emotion": "model:qwen0.6bemo4-merge/model.safetensors"
      }
    }
  ]
}