diodiogod-TTS-Audio-Suite/utils/audio_cpp/model_specs/qwen3_tts.json

{
  "family": "qwen3_tts",
  "display_name": "Qwen3-TTS",
  "description": "Qwen TTS family for controllable 10-language speech synthesis, including 3-second voice cloning, CustomVoice instruction control over preset timbres, and VoiceDesign from natural-language descriptions.",
  "category": "tts",
  "status": "supported",
  "tasks": [
    "tts",
    "clone",
    "design"
  ],
  "modes": [
    "offline"
  ],
  "languages": [
    "zh",
    "en",
    "ja",
    "ko",
    "de",
    "fr",
    "ru",
    "pt",
    "es",
    "it"
  ],
  "capabilities": {
    "clone": [
      "speaker_reference"
    ],
    "design": [
      "voice_design"
    ]
  },
  "runtime": {
    "tags": [
      "gguf"
    ]
  },
  "ui": {
    "recommended_package": "qwen3_tts_1_7b_base_q8_0",
    "tags": [
      "TTS",
      "Clone",
      "Design",
      "GGUF"
    ],
    "docs": [
      "docs/models/qwen3.md",
      "docs/tts.md",
      "docs/gguf.md"
    ]
  },
  "package_defaults": {
    "download": {
      "kind": "huggingface_snapshot",
      "repo": "audio-cpp/audio.cpp-gguf",
      "revision": "main",
      "gated": false
    }
  },
  "packages": [
    {
      "id": "qwen3_tts_1_7b_base_q8_0",
      "display_name": "Qwen3 TTS 12Hz 1.7B Base Q8_0 GGUF",
      "default": true,
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "Qwen3-TTS-12Hz-1.7B-Base-GGUF",
      "files": [
        "Qwen3-TTS-12Hz-1.7B-Base-GGUF/qwen3-tts-12hz-1.7b-base-q8_0_v2.gguf"
      ],
      "strip_prefix": "Qwen3-TTS-12Hz-1.7B-Base-GGUF"
    },
    {
      "id": "qwen3_tts_1_7b_base_bf16",
      "display_name": "Qwen3 TTS 12Hz 1.7B Base BF16 GGUF",
      "format": "gguf",
      "precision": "bf16",
      "target_directory": "Qwen3-TTS-12Hz-1.7B-Base-GGUF",
      "files": [
        "Qwen3-TTS-12Hz-1.7B-Base-GGUF/qwen3-tts-12hz-1.7b-base-bf16.gguf"
      ],
      "strip_prefix": "Qwen3-TTS-12Hz-1.7B-Base-GGUF"
    },
    {
      "id": "qwen3_tts_1_7b_base_orig",
      "display_name": "Qwen3 TTS 12Hz 1.7B Base Original-Dtype GGUF",
      "format": "gguf",
      "precision": "orig",
      "target_directory": "Qwen3-TTS-12Hz-1.7B-Base-GGUF",
      "files": [
        "Qwen3-TTS-12Hz-1.7B-Base-GGUF/qwen3-tts-12hz-1.7b-base-orig.gguf"
      ],
      "strip_prefix": "Qwen3-TTS-12Hz-1.7B-Base-GGUF"
    },
    {
      "id": "qwen3_tts_1_7b_customvoice_q8_0",
      "display_name": "Qwen3 TTS 12Hz 1.7B CustomVoice Q8_0 GGUF",
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF",
      "files": [
        "Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF/qwen3-tts-12hz-1.7b-customvoice-q8_0.gguf"
      ],
      "strip_prefix": "Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF"
    },
    {
      "id": "qwen3_tts_1_7b_customvoice_bf16",
      "display_name": "Qwen3 TTS 12Hz 1.7B CustomVoice BF16 GGUF",
      "format": "gguf",
      "precision": "bf16",
      "target_directory": "Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF",
      "files": [
        "Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF/qwen3-tts-12hz-1.7b-customvoice-bf16.gguf"
      ],
      "strip_prefix": "Qwen3-TTS-12Hz-1.7B-CustomVoice-GGUF"
    },
    {
      "id": "qwen3_tts_1_7b_voicedesign_q8_0",
      "display_name": "Qwen3 TTS 12Hz 1.7B VoiceDesign Q8_0 GGUF",
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF",
      "files": [
        "Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF/qwen3-tts-12hz-1.7b-voicedesign-q8_0.gguf"
      ],
      "strip_prefix": "Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF"
    },
    {
      "id": "qwen3_tts_1_7b_voicedesign_bf16",
      "display_name": "Qwen3 TTS 12Hz 1.7B VoiceDesign BF16 GGUF",
      "format": "gguf",
      "precision": "bf16",
      "target_directory": "Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF",
      "files": [
        "Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF/qwen3-tts-12hz-1.7b-voicedesign-bf16.gguf"
      ],
      "strip_prefix": "Qwen3-TTS-12Hz-1.7B-VoiceDesign-GGUF"
    },
    {
      "id": "qwen3_tts_1_7b_base_safetensors",
      "display_name": "Qwen3 TTS 12Hz 1.7B Base Safetensors",
      "format": "safetensors",
      "precision": "native",
      "target_directory": "Qwen3-TTS-12Hz-1.7B-Base",
      "files": [
        "config.json",
        "generation_config.json",
        "model.safetensors",
        "speech_tokenizer/config.json",
        "speech_tokenizer/model.safetensors",
        "tokenizer_config.json"
      ],
      "download": {
        "kind": "huggingface_snapshot",
        "repo": "Qwen/Qwen3-TTS-12Hz-1.7B-Base"
      }
    },
    {
      "id": "qwen3_tts_0_6b_base_safetensors",
      "display_name": "Qwen3 TTS 12Hz 0.6B Base Safetensors",
      "format": "safetensors",
      "precision": "native",
      "target_directory": "Qwen3-TTS-12Hz-0.6B-Base",
      "files": [
        "config.json",
        "generation_config.json",
        "model.safetensors",
        "speech_tokenizer/config.json",
        "speech_tokenizer/model.safetensors",
        "tokenizer_config.json"
      ],
      "download": {
        "kind": "huggingface_snapshot",
        "repo": "Qwen/Qwen3-TTS-12Hz-0.6B-Base"
      }
    }
  ],
  "sources": [
    {
      "format": "gguf",
      "roots": {
        "model": ".",
        "weights": "$gguf"
      },
      "files": {
        "config": "model:config.json",
        "generation_config": "model:generation_config.json",
        "tokenizer_config": "model:tokenizer_config.json",
        "vocab": "model:vocab.json",
        "merges": "model:merges.txt",
        "speech_tokenizer_config": "model:speech_tokenizer/config.json"
      },
      "tensors": {
        "model_weights": {
          "source": "weights:",
          "prefix": "model_weights"
        },
        "speech_tokenizer_weights": {
          "source": "weights:",
          "prefix": "speech_tokenizer_weights"
        }
      }
    },
    {
      "format": "safetensors",
      "roots": {
        "model": "."
      },
      "files": {
        "config": "model:config.json",
        "generation_config": "model:generation_config.json",
        "tokenizer_config": "model:tokenizer_config.json",
        "vocab": "model:vocab.json",
        "merges": "model:merges.txt",
        "speech_tokenizer_config": "model:speech_tokenizer/config.json"
      },
      "tensors": {
        "model_weights": "model:model.safetensors",
        "speech_tokenizer_weights": "model:speech_tokenizer/model.safetensors"
      }
    }
  ]
}