{
  "schema_version": 1,
  "family": "voxcpm1",
  "display_name": "VoxCPM1",
  "description": "OpenBMB VoxCPM 0.5B tokenizer-free TTS model supporting short-reference voice cloning and streaming output (16kHz).",
  "category": "tts",
  "status": "supported",
  "tasks": [
    "tts",
    "clone"
  ],
  "modes": [
    "offline",
    "streaming"
  ],
  "languages": [
    "zh",
    "en",
    "ja",
    "ko"
  ],
  "capabilities": {
    "clone": [
      "speaker_reference"
    ]
  },
  "dependencies": [],
  "options": {
    "request": [
      {
        "name": "text_chunk_mode",
        "type": "enum",
        "description": "Text chunking mode; default tag_aware.",
        "preset": "text_chunk_mode_full",
        "required": false,
        "default": "tag_aware"
      },
      {
        "name": "seed",
        "type": "int",
        "description": "Random seed for MiniCPM and diffusion sampling.",
        "required": false
      },
      {
        "name": "max_tokens",
        "type": "int",
        "description": "Maximum MiniCPM output tokens.",
        "required": false,
        "default": 1024
      },
      {
        "name": "min_tokens",
        "type": "int",
        "description": "Minimum MiniCPM output tokens before an EOS stop is honored.",
        "required": false,
        "default": 0
      },
      {
        "name": "num_inference_steps",
        "type": "int",
        "description": "CFM diffusion sampling steps.",
        "required": false,
        "default": 50
      },
      {
        "name": "guidance_scale",
        "type": "float",
        "description": "CFM classifier-free guidance rate.",
        "required": false,
        "default": 2.0
      },
      {
        "name": "retry_badcase",
        "type": "bool",
        "description": "Retry the request when generation is detected as a bad case.",
        "required": false,
        "default": true
      },
      {
        "name": "retry_badcase_max_times",
        "type": "int",
        "description": "Maximum bad-case retry count.",
        "required": false,
        "default": 2
      },
      {
        "name": "retry_badcase_ratio_threshold",
        "type": "float",
        "description": "Bad-case ratio threshold for retry decisions.",
        "required": false
      },
      {
        "name": "prompt_text",
        "type": "string",
        "description": "Text prompt for prompt-continuation voice cloning.",
        "required": false
      },
      {
        "name": "reference_text",
        "type": "string",
        "description": "Alias for prompt_text; text prompt for prompt-continuation voice cloning.",
        "required": false
      }
    ],
    "session": [
      {
        "name": "mem_saver",
        "type": "bool",
        "description": "Use tighter graph workspaces and release request runtime graphs; default false.",
        "required": false,
        "default": false
      },
      {
        "name": "prompt_cache_slots",
        "type": "int",
        "description": "Prompt and prompt-audio embedding cache slots; default 1.",
        "required": false,
        "default": 1
      },
      {
        "name": "weight_type",
        "type": "enum",
        "description": "Model weight storage type.",
        "preset": "weight_type_full",
        "required": false,
        "default": "native"
      },
      {
        "name": "audiovae_weight_type",
        "type": "enum",
        "description": "AudioVAE weight storage type.",
        "preset": "weight_type_full",
        "required": false,
        "default": "native"
      },
      {
        "name": "weight_context_mb",
        "type": "int",
        "description": "Model weight graph context size in MB.",
        "required": false
      },
      {
        "name": "text_embedding_graph_context_mb",
        "type": "int",
        "description": "Text embedding graph context size in MB.",
        "required": false
      },
      {
        "name": "lm_step_graph_context_mb",
        "type": "int",
        "description": "LM step graph context size in MB.",
        "required": false
      },
      {
        "name": "projection_graph_context_mb",
        "type": "int",
        "description": "Projection graph context size in MB.",
        "required": false
      },
      {
        "name": "local_encoder_graph_context_mb",
        "type": "int",
        "description": "Local encoder graph context size in MB.",
        "required": false
      },
      {
        "name": "dit_graph_context_mb",
        "type": "int",
        "description": "DiT estimator graph context size in MB.",
        "required": false
      },
      {
        "name": "audiovae_weight_context_mb",
        "type": "int",
        "description": "AudioVAE weight graph context size in MB.",
        "required": false
      },
      {
        "name": "audiovae_graph_context_mb",
        "type": "int",
        "description": "AudioVAE decoder graph context size in MB.",
        "required": false
      },
      {
        "name": "audiovae_encoder_graph_context_mb",
        "type": "int",
        "description": "AudioVAE encoder graph context size in MB.",
        "required": false
      },
      {
        "name": "audiovae_latent_capacity",
        "type": "int",
        "description": "AudioVAE decoder latent frame capacity.",
        "required": false
      },
      {
        "name": "audiovae_encoder_sample_capacity",
        "type": "int",
        "description": "AudioVAE encoder sample capacity.",
        "required": false
      }
    ],
    "load": [
      {
        "name": "weight_type",
        "type": "enum",
        "description": "Model weight storage type selected at load time.",
        "preset": "weight_type_full",
        "required": false,
        "default": "native"
      },
      {
        "name": "audiovae_weight_type",
        "type": "enum",
        "description": "AudioVAE weight storage type selected at load time.",
        "preset": "weight_type_full",
        "required": false,
        "default": "native"
      }
    ]
  },
  "runtime": {
    "tags": [
      "gguf",
      "stream"
    ]
  },
  "ui": {
    "recommended_package": "voxcpm1_0_5b_q8_0",
    "tags": [
      "TTS",
      "Clone",
      "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": "voxcpm1_0_5b_q8_0",
      "display_name": "VoxCPM 0.5B Q8_0 GGUF",
      "default": true,
      "format": "gguf",
      "precision": "q8_0",
      "target_directory": "VoxCPM1-GGUF",
      "files": [
        "VoxCPM1-GGUF/voxcpm-0.5b-q8_0-audiovae-f16.gguf"
      ],
      "strip_prefix": "VoxCPM1-GGUF"
    }
  ],
  "sources": [
    {
      "format": "gguf",
      "roots": {
        "model": ".",
        "weights": "$gguf"
      },
      "files": {
        "config": "model:config.json",
        "tokenizer_json": "model:tokenizer.json",
        "tokenizer_config": "model:tokenizer_config.json"
      },
      "optional_files": {
        "special_tokens_map": "model:special_tokens_map.json"
      },
      "tensors": {
        "weights": {
          "source": "weights:"
        },
        "audiovae_weights": {
          "source": "weights:"
        }
      }
    }
  ]
}