{
  "family": "voxcpm2",
  "display_name": "VoxCPM2",
  "description": "OpenBMB tokenizer-free TTS model supporting 30 languages and 9 Chinese dialects, with 48 kHz output, natural-language voice design, controllable short-reference voice cloning, and expressive style guidance.",
  "category": "tts",
  "status": "supported",
  "tasks": [
    "tts",
    "clone",
    "design"
  ],
  "modes": [
    "offline",
    "streaming"
  ],
  "languages": [
    "ar",
    "my",
    "zh",
    "zh dialects",
    "da",
    "nl",
    "en",
    "fi",
    "fr",
    "de",
    "el",
    "he",
    "hi",
    "id",
    "it",
    "ja",
    "km",
    "ko",
    "lo",
    "ms",
    "no",
    "pl",
    "pt",
    "ru",
    "es",
    "sw",
    "sv",
    "tl",
    "th",
    "tr",
    "vi"
  ],
  "capabilities": {
    "clone": [
      "speaker_reference"
    ],
    "design": [
      "voice_design"
    ]
  },
  "runtime": {
    "tags": [
      "gguf",
      "stream"
    ]
  },
  "ui": {
    "recommended_package": "voxcpm2_q8_0",
    "tags": [
      "TTS",
      "Clone",
      "Design",
      "GGUF",
      "Stream"
    ],
    "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": "voxcpm2_q8_0",
      "display_name": "VoxCPM2 Q8_0 GGUF",
      "default": true,
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "VoxCPM2-GGUF",
      "files": [
        "VoxCPM2-GGUF/voxcpm2-q8_0.gguf"
      ],
      "strip_prefix": "VoxCPM2-GGUF"
    },
    {
      "id": "voxcpm2_bf16",
      "display_name": "VoxCPM2 BF16 GGUF",
      "format": "gguf",
      "precision": "bf16",
      "target_directory": "VoxCPM2-GGUF",
      "files": [
        "VoxCPM2-GGUF/voxcpm2-bf16.gguf"
      ],
      "strip_prefix": "VoxCPM2-GGUF"
    },
    {
      "id": "voxcpm2_orig",
      "display_name": "VoxCPM2 Original-Dtype GGUF",
      "format": "gguf",
      "precision": "orig",
      "target_directory": "VoxCPM2-GGUF",
      "files": [
        "VoxCPM2-GGUF/voxcpm2-orig.gguf"
      ],
      "strip_prefix": "VoxCPM2-GGUF"
    },
    {
      "id": "voxcpm2_safetensors",
      "display_name": "VoxCPM2 Safetensors",
      "format": "safetensors",
      "precision": "native",
      "target_directory": "VoxCPM2",
      "files": [
        "config.json",
        "model.safetensors",
        "tokenizer.json",
        "tokenizer_config.json"
      ],
      "download": {
        "kind": "huggingface_snapshot",
        "repo": "OpenBMB/VoxCPM2"
      }
    }
  ],
  "sources": [
    {
      "format": "gguf",
      "roots": {
        "model": ".",
        "weights": "$gguf"
      },
      "files": {
        "config": "model:config.json",
        "tokenizer_config": "model:tokenizer_config.json",
        "tokenizer_json": "model:tokenizer.json",
        "special_tokens_map": "model:special_tokens_map.json"
      },
      "tensors": {
        "weights": {
          "source": "weights:",
          "prefix": "weights"
        },
        "audiovae_weights": {
          "source": "weights:",
          "prefix": "audiovae_weights"
        }
      }
    },
    {
      "format": "safetensors",
      "roots": {
        "model": "."
      },
      "files": {
        "config": "model:config.json",
        "tokenizer_config": "model:tokenizer_config.json",
        "tokenizer_json": "model:tokenizer.json",
        "special_tokens_map": "model:special_tokens_map.json"
      },
      "tensors": {
        "weights": "model:model.safetensors",
        "audiovae_weights": "model:audiovae.safetensors"
      }
    }
  ]
}