{
  "schemaVersion": "1.0",
  "item": {
    "slug": "qwen-tts",
    "name": "Qwen3-tts",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/paki81/qwen-tts",
    "canonicalUrl": "https://clawhub.ai/paki81/qwen-tts",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/qwen-tts",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qwen-tts",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "MAC_SERVER.md",
      "README.md",
      "SKILL.md",
      "VOICEDESIGN.md",
      "scripts/server.py",
      "scripts/setup.sh"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/qwen-tts"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/qwen-tts",
    "agentPageUrl": "https://openagent3.xyz/skills/qwen-tts/agent",
    "manifestUrl": "https://openagent3.xyz/skills/qwen-tts/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/qwen-tts/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Qwen TTS",
        "body": "Local text-to-speech using Hugging Face's Qwen3-TTS-12Hz-1.7B-CustomVoice model."
      },
      {
        "title": "Quick Start",
        "body": "Generate speech from text:\n\nscripts/tts.py \"Ciao, come va?\" -l Italian -o output.wav\n\nWith voice instruction (emotion/style):\n\nscripts/tts.py \"Sono felice!\" -i \"Parla con entusiasmo\" -l Italian -o happy.wav\n\nDifferent speaker:\n\nscripts/tts.py \"Hello world\" -s Ryan -l English -o hello.wav"
      },
      {
        "title": "Installation",
        "body": "First-time setup (one-time):\n\ncd skills/public/qwen-tts\nbash scripts/setup.sh\n\nThis creates a local virtual environment and installs qwen-tts package (~500MB).\n\nNote: First synthesis downloads ~1.7GB model from Hugging Face automatically."
      },
      {
        "title": "Usage",
        "body": "scripts/tts.py [options] \"Text to speak\""
      },
      {
        "title": "Options",
        "body": "-o, --output PATH - Output file path (default: qwen_output.wav)\n-s, --speaker NAME - Speaker voice (default: Vivian)\n-l, --language LANG - Language (default: Auto)\n-i, --instruct TEXT - Voice instruction (emotion, style, tone)\n--list-speakers - Show available speakers\n--model NAME - Model name (default: CustomVoice 1.7B)"
      },
      {
        "title": "Examples",
        "body": "Basic Italian speech:\n\nscripts/tts.py \"Benvenuto nel futuro del text-to-speech\" -l Italian -o welcome.wav\n\nWith emotion/instruction:\n\nscripts/tts.py \"Sono molto felice di vederti!\" -i \"Parla con entusiasmo e gioia\" -l Italian -o happy.wav\n\nDifferent speaker:\n\nscripts/tts.py \"Hello, nice to meet you\" -s Ryan -l English -o ryan.wav\n\nList available speakers:\n\nscripts/tts.py --list-speakers"
      },
      {
        "title": "Available Speakers",
        "body": "The CustomVoice model includes 9 premium voices:\n\nSpeakerLanguageDescriptionVivianChineseBright, slightly edgy young femaleSerenaChineseWarm, gentle young femaleUncle_FuChineseSeasoned male, low mellow timbreDylanChinese (Beijing)Youthful Beijing male, clearEricChinese (Sichuan)Lively Chengdu male, huskyRyanEnglishDynamic male, rhythmicAidenEnglishSunny American maleOno_AnnaJapanesePlayful female, light nimbleSoheeKoreanWarm female, rich emotion\n\nRecommendation: Use each speaker's native language for best quality, though all speakers support all 10 languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian)."
      },
      {
        "title": "Voice Instructions",
        "body": "Use -i, --instruct to control emotion, tone, and style:\n\nItalian examples:\n\n\"Parla con entusiasmo\"\n\"Tono serio e professionale\"\n\"Voce calma e rilassante\"\n\"Leggi come un narratore\"\n\nEnglish examples:\n\n\"Speak with excitement\"\n\"Very happy and energetic\"\n\"Calm and soothing voice\"\n\"Read like a narrator\""
      },
      {
        "title": "Integration with OpenClaw",
        "body": "The script outputs the audio file path to stdout (last line), making it compatible with OpenClaw's TTS workflow:\n\n# OpenClaw captures the output path\ncd skills/public/qwen-tts\nOUTPUT=$(scripts/tts.py \"Ciao\" -s Vivian -l Italian -o /tmp/audio.wav 2>/dev/null)\n# OUTPUT = /tmp/audio.wav"
      },
      {
        "title": "Performance",
        "body": "GPU (CUDA): ~1-3 seconds for short phrases\nCPU: ~10-30 seconds for short phrases\nModel size: ~1.7GB (auto-downloads on first run)\nVenv size: ~500MB (installed dependencies)"
      },
      {
        "title": "Troubleshooting",
        "body": "Setup fails:\n\n# Ensure Python 3.10-3.12 is available\npython3.12 --version\n\n# Re-run setup\ncd skills/public/qwen-tts\nrm -rf venv\nbash scripts/setup.sh\n\nModel download slow/fails:\n\n# Use mirror (China mainland)\nexport HF_ENDPOINT=https://hf-mirror.com\nscripts/tts.py \"Test\" -o test.wav\n\nOut of memory (GPU):\nThe model automatically falls back to CPU if GPU memory insufficient.\n\nAudio quality issues:\n\nTry different speaker: --list-speakers\nAdd instruction: -i \"Speak clearly and slowly\"\nCheck language matches text: -l Italian for Italian text"
      },
      {
        "title": "Model Details",
        "body": "Model: Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice\nSource: Hugging Face (https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice)\nLicense: Check model card for current license terms\nSample Rate: 16kHz\nOutput Format: WAV (uncompressed)"
      }
    ],
    "body": "Qwen TTS\n\nLocal text-to-speech using Hugging Face's Qwen3-TTS-12Hz-1.7B-CustomVoice model.\n\nQuick Start\n\nGenerate speech from text:\n\nscripts/tts.py \"Ciao, come va?\" -l Italian -o output.wav\n\n\nWith voice instruction (emotion/style):\n\nscripts/tts.py \"Sono felice!\" -i \"Parla con entusiasmo\" -l Italian -o happy.wav\n\n\nDifferent speaker:\n\nscripts/tts.py \"Hello world\" -s Ryan -l English -o hello.wav\n\nInstallation\n\nFirst-time setup (one-time):\n\ncd skills/public/qwen-tts\nbash scripts/setup.sh\n\n\nThis creates a local virtual environment and installs qwen-tts package (~500MB).\n\nNote: First synthesis downloads ~1.7GB model from Hugging Face automatically.\n\nUsage\nscripts/tts.py [options] \"Text to speak\"\n\nOptions\n-o, --output PATH - Output file path (default: qwen_output.wav)\n-s, --speaker NAME - Speaker voice (default: Vivian)\n-l, --language LANG - Language (default: Auto)\n-i, --instruct TEXT - Voice instruction (emotion, style, tone)\n--list-speakers - Show available speakers\n--model NAME - Model name (default: CustomVoice 1.7B)\nExamples\n\nBasic Italian speech:\n\nscripts/tts.py \"Benvenuto nel futuro del text-to-speech\" -l Italian -o welcome.wav\n\n\nWith emotion/instruction:\n\nscripts/tts.py \"Sono molto felice di vederti!\" -i \"Parla con entusiasmo e gioia\" -l Italian -o happy.wav\n\n\nDifferent speaker:\n\nscripts/tts.py \"Hello, nice to meet you\" -s Ryan -l English -o ryan.wav\n\n\nList available speakers:\n\nscripts/tts.py --list-speakers\n\nAvailable Speakers\n\nThe CustomVoice model includes 9 premium voices:\n\nSpeaker\tLanguage\tDescription\nVivian\tChinese\tBright, slightly edgy young female\nSerena\tChinese\tWarm, gentle young female\nUncle_Fu\tChinese\tSeasoned male, low mellow timbre\nDylan\tChinese (Beijing)\tYouthful Beijing male, clear\nEric\tChinese (Sichuan)\tLively Chengdu male, husky\nRyan\tEnglish\tDynamic male, rhythmic\nAiden\tEnglish\tSunny American male\nOno_Anna\tJapanese\tPlayful female, light nimble\nSohee\tKorean\tWarm female, rich emotion\n\nRecommendation: Use each speaker's native language for best quality, though all speakers support all 10 languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian).\n\nVoice Instructions\n\nUse -i, --instruct to control emotion, tone, and style:\n\nItalian examples:\n\n\"Parla con entusiasmo\"\n\"Tono serio e professionale\"\n\"Voce calma e rilassante\"\n\"Leggi come un narratore\"\n\nEnglish examples:\n\n\"Speak with excitement\"\n\"Very happy and energetic\"\n\"Calm and soothing voice\"\n\"Read like a narrator\"\nIntegration with OpenClaw\n\nThe script outputs the audio file path to stdout (last line), making it compatible with OpenClaw's TTS workflow:\n\n# OpenClaw captures the output path\ncd skills/public/qwen-tts\nOUTPUT=$(scripts/tts.py \"Ciao\" -s Vivian -l Italian -o /tmp/audio.wav 2>/dev/null)\n# OUTPUT = /tmp/audio.wav\n\nPerformance\nGPU (CUDA): ~1-3 seconds for short phrases\nCPU: ~10-30 seconds for short phrases\nModel size: ~1.7GB (auto-downloads on first run)\nVenv size: ~500MB (installed dependencies)\nTroubleshooting\n\nSetup fails:\n\n# Ensure Python 3.10-3.12 is available\npython3.12 --version\n\n# Re-run setup\ncd skills/public/qwen-tts\nrm -rf venv\nbash scripts/setup.sh\n\n\nModel download slow/fails:\n\n# Use mirror (China mainland)\nexport HF_ENDPOINT=https://hf-mirror.com\nscripts/tts.py \"Test\" -o test.wav\n\n\nOut of memory (GPU): The model automatically falls back to CPU if GPU memory insufficient.\n\nAudio quality issues:\n\nTry different speaker: --list-speakers\nAdd instruction: -i \"Speak clearly and slowly\"\nCheck language matches text: -l Italian for Italian text\nModel Details\nModel: Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice\nSource: Hugging Face (https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice)\nLicense: Check model card for current license terms\nSample Rate: 16kHz\nOutput Format: WAV (uncompressed)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/paki81/qwen-tts",
    "publisherUrl": "https://clawhub.ai/paki81/qwen-tts",
    "owner": "paki81",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/qwen-tts",
    "downloadUrl": "https://openagent3.xyz/downloads/qwen-tts",
    "agentUrl": "https://openagent3.xyz/skills/qwen-tts/agent",
    "manifestUrl": "https://openagent3.xyz/skills/qwen-tts/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/qwen-tts/agent.md"
  }
}