{
  "family": "chatterbox",
  "display_name": "Chatterbox",
  "description": "Open-source Chatterbox family for expressive TTS and voice conversion, with emotion exaggeration control, fast generation, zero-shot voice cloning, and an integrated multilingual TTS path.",
  "category": "tts",
  "status": "supported",
  "tasks": [
    "tts",
    "clone",
    "vc"
  ],
  "modes": [
    "offline"
  ],
  "languages": [
    "ar",
    "da",
    "de",
    "el",
    "en",
    "es",
    "fi",
    "fr",
    "hi",
    "it",
    "ko",
    "ms",
    "nl",
    "no",
    "pl",
    "pt",
    "sv",
    "sw",
    "tr"
  ],
  "capabilities": {
    "clone": [
      "speaker_reference"
    ],
    "vc": [
      "speaker_reference"
    ]
  },
  "runtime": {
    "tags": [
      "gguf"
    ]
  },
  "ui": {
    "recommended_package": "chatterbox_q8_0",
    "tags": [
      "TTS",
      "Clone",
      "VC",
      "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": "chatterbox_q8_0",
      "display_name": "Chatterbox Q8_0 GGUF",
      "default": true,
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "Chatterbox-GGUF",
      "files": [
        "Chatterbox-GGUF/chatterbox-q8_0.gguf"
      ],
      "strip_prefix": "Chatterbox-GGUF"
    },
    {
      "id": "chatterbox_f16",
      "display_name": "Chatterbox F16 GGUF",
      "format": "gguf",
      "precision": "f16",
      "target_directory": "Chatterbox-GGUF",
      "files": [
        "Chatterbox-GGUF/chatterbox-f16.gguf"
      ],
      "strip_prefix": "Chatterbox-GGUF"
    },
    {
      "id": "chatterbox_safetensors",
      "display_name": "Chatterbox Safetensors",
      "format": "safetensors",
      "precision": "native",
      "target_directory": "chatterbox",
      "files": [
        "ve.safetensors",
        "t3_cfg.safetensors",
        "s3gen.safetensors",
        "tokenizer.json"
      ],
      "download": {
        "kind": "huggingface_snapshot",
        "repo": "ResembleAI/chatterbox"
      }
    }
  ],
  "sources": [
    {
      "format": "gguf",
      "roots": {
        "model": ".",
        "weights": "$gguf"
      },
      "files": {
        "english_tokenizer": "model:tokenizer.json",
        "multilingual_tokenizer": "model:grapheme_mtl_merged_expanded_v1.json",
        "cangjie_mapping": "model:Cangjie5_TC.json",
        "builtin_conditionals": "model:conds.pt"
      },
      "tensors": {
        "voice_encoder_weights": {
          "source": "weights:",
          "prefix": "voice_encoder"
        },
        "s3gen_weights": {
          "source": "weights:",
          "prefix": "s3gen"
        },
        "t3_english_weights": {
          "source": "weights:",
          "prefix": "t3_english"
        },
        "t3_multilingual_v2_weights": {
          "source": "weights:",
          "prefix": "t3_multilingual_v2"
        },
        "t3_multilingual_v3_weights": {
          "source": "weights:",
          "prefix": "t3_multilingual_v3"
        }
      }
    },
    {
      "format": "safetensors",
      "roots": {
        "model": "."
      },
      "files": {
        "english_tokenizer": "model:tokenizer.json",
        "multilingual_tokenizer": "model:grapheme_mtl_merged_expanded_v1.json",
        "cangjie_mapping": "model:Cangjie5_TC.json",
        "builtin_conditionals": "model:conds.pt"
      },
      "tensors": {
        "voice_encoder_weights": "model:ve.safetensors",
        "s3gen_weights": "model:s3gen.safetensors",
        "t3_english_weights": "model:t3_cfg.safetensors",
        "t3_multilingual_v2_weights": "model:t3_mtl23ls_v2.safetensors",
        "t3_multilingual_v3_weights": "model:t3_mtl23ls_v3.safetensors"
      }
    }
  ]
}