{
  "schemaVersion": "1.0",
  "updates": [],
  "companyNews": [],
  "id": "b898",
  "language": "zh",
  "name": "Qwen3-TTS",
  "originalName": "Qwen3-TTS",
  "library": "tools",
  "category": "音频音乐",
  "categoryKey": "音频音乐",
  "categoryKeys": [
    "音频音乐"
  ],
  "categories": [
    "音频音乐"
  ],
  "entryPoints": [],
  "summary": "按 VoiceDesign、CustomVoice 或 Base 型号选择文字设计音色、预设声音控制或参考语音复现，覆盖十种语言。",
  "introduction": "Qwen3-TTS 将语音生成分成不同检查点：VoiceDesign 根据自然语言描述设计新声音，CustomVoice 使用预设说话人，Base 用参考音频复现音色并可用于微调。公开模型覆盖十种语言，但指令控制能力随型号而异，例如 0.6B 与 1.7B 不能一概而论。提供 Python、本地 WebUI、流式与非流式工作流；托管 API 另需对应账户与服务配置，主代码及所核对的官方模型卡声明 Apache 2.0。",
  "capabilities": [],
  "company": {
    "name": "通义千问团队",
    "originalName": "Qwen Team",
    "country": {
      "codes": [
        "CN"
      ],
      "names": [
        "中国"
      ],
      "display": "中国",
      "basis": "headquarters",
      "basisLabel": "公司总部"
    }
  },
  "officialUrl": "https://github.com/QwenLM/Qwen3-TTS",
  "profileUpdatedOn": "2026-10-20",
  "sources": [
    {
      "kind": "product",
      "url": "https://github.com/QwenLM/Qwen3-TTS"
    },
    {
      "kind": "documentation",
      "url": "https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign"
    }
  ],
  "news": [],
  "links": {
    "interactive": "products/qwen3-tts--b898.html",
    "reading": "read/zh/products/qwen3-tts--b898.html",
    "markdown": "read/zh/products/qwen3-tts--b898.md",
    "json": "read/zh/products/qwen3-tts--b898.json"
  }
}