{
  "schemaVersion": "1.0",
  "updates": [],
  "companyNews": [],
  "id": "b898",
  "language": "en",
  "name": "Qwen3-TTS",
  "originalName": "Qwen3-TTS",
  "library": "tools",
  "category": "Audio & music",
  "categoryKey": "音频音乐",
  "categoryKeys": [
    "音频音乐"
  ],
  "categories": [
    "Audio & music"
  ],
  "entryPoints": [],
  "summary": "Choose VoiceDesign, CustomVoice or Base checkpoints for described voices, preset-voice control or reference cloning across ten languages.",
  "introduction": "Qwen3-TTS separates tasks by checkpoint: VoiceDesign creates voices from descriptions, CustomVoice uses preset speakers, and Base reproduces reference voices and supports fine-tuning. Released models cover ten languages, but instruction control differs between sizes and variants. Python, local WebUI, streaming and non-streaming workflows are documented. Hosted APIs require separate account and service configuration. Main code and the reviewed official model card declare Apache 2.0.",
  "capabilities": [],
  "company": {
    "name": "Qwen Team",
    "originalName": "Qwen Team",
    "country": {
      "codes": [
        "CN"
      ],
      "names": [
        "China"
      ],
      "display": "China",
      "basis": "headquarters",
      "basisLabel": "Company headquarters"
    }
  },
  "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/en/products/qwen3-tts--b898.html",
    "markdown": "read/en/products/qwen3-tts--b898.md",
    "json": "read/en/products/qwen3-tts--b898.json"
  }
}