{
  "schemaVersion": "1.0",
  "item": {
    "slug": "mm-easy-voice",
    "name": "mmEasyVoice",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/BLUE-coconut/mm-easy-voice",
    "canonicalUrl": "https://clawhub.ai/BLUE-coconut/mm-easy-voice",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/mm-easy-voice",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mm-easy-voice",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "check_environment.py",
      "mmvoice.py",
      "reference/audio-guide.md",
      "reference/getting-started.md",
      "reference/troubleshooting.md"
    ],
    "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. 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. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/mm-easy-voice"
    },
    "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/mm-easy-voice",
    "agentPageUrl": "https://openagent3.xyz/skills/mm-easy-voice/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mm-easy-voice/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mm-easy-voice/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "MiniMax Easy Voice",
        "body": "Simple text-to-speech skill powered by MiniMax Voice API. Converts any text into natural-sounding audio with customizable voice selection."
      },
      {
        "title": "[Step 1] Preparation",
        "body": "IMPORTANT: Before using this skill, always verify the environment:\n\npython check_environment.py\n\nIf API key is not set:\n\nexport MINIMAX_VOICE_API_KEY=\"your-api-key-here\"\n\nRequirements:\n\nPython 3.8+\nMINIMAX_VOICE_API_KEY environment variable (required)\nFFmpeg (optional, for audio merging/conversion)"
      },
      {
        "title": "[Step 2] Generate speech audio from text",
        "body": "Convert any text to speech in one command:\n\n# Default voice (male-qn-qingse)\npython mmvoice.py tts \"Hello, this is a test.\" -o test.mp3\n\n# Chinese text\npython mmvoice.py tts \"你好，这是一个测试。\" -o test_cn.mp3\n\n# Specify a different voice by \"-v voice_id\"\npython mmvoice.py tts \"Hello world\" -v female-shaonv -o hello.mp3\n\n# Specify output path\npython mmvoice.py tts \"Your text\" -o /path/to/output.mp3\n\nRequired parameters:\n\ntext: The text you want to convert to speech\n-o OUTPUT: Output audio file path (required)\n\nOptional parameters:\n\n-v VOICE_ID: Voice to use (default: male-qn-qingse)"
      },
      {
        "title": "Usage Details",
        "body": "Text length limits:\n\nUp to 10,000 characters per request\nFor longer text, split into multiple requests and merge later\n\nPause insertion: Use <#x#> where x = pause duration in seconds\n\nExample: \"Hello<#1.5#>world\" = 1.5 second pause between words\nRange: 0.01 to 99.99 seconds\n\nEmotion matching: speech-2.8 models automatically match emotions to your text content"
      },
      {
        "title": "Voice Selection",
        "body": "Choose the right voice for your content by consulting the voice catalog:\n\n# List all available voices\npython mmvoice.py list-voices\n\nVoice catalog: reference/voice_catalog.md\n\nContains:\n\nAll available system voices (male, female)\nVoice characteristics and recommended use cases\nHow to select the right voice for your content"
      },
      {
        "title": "Voice Management",
        "body": "List available voices:\n\npython mmvoice.py list-voices\n\nClone a voice from audio sample:\n\npython mmvoice.py clone audio_file.mp3 --voice-id my-custom-voice\n\nDesign a voice from description:\n\npython mmvoice.py design \"A warm, gentle female voice\" --voice-id designed-voice"
      },
      {
        "title": "Audio Processing",
        "body": "Merge multiple audio files:\n\npython mmvoice.py merge file1.mp3 file2.mp3 file3.mp3 -o combined.mp3\n\nConvert audio format:\n\npython mmvoice.py convert input.wav -o output.mp3 --format mp3"
      },
      {
        "title": "Reference Documents",
        "body": "Open these when needed for more details:\n\n|| Document | When to Use |\n||----------|-------------|\n|| reference/voice_catalog.md | Choosing a voice_id |\n|| reference/getting-started.md | Environment setup |\n|| reference/audio-guide.md | Audio processing |\n|| reference/voice-guide.md | Voice cloning and design |\n|| reference/troubleshooting.md | Common issues and solutions |"
      },
      {
        "title": "Troubleshooting",
        "body": "Common issues:\n\nAPI key not set: Run export MINIMAX_VOICE_API_KEY=\"your-key\"\nFFmpeg missing: Install with brew install ffmpeg (macOS) or sudo apt install ffmpeg (Ubuntu)\nVoice not found: Use python mmvoice.py list-voices to see available voices\n\nRun environment check:\n\npython check_environment.py\n\nSee reference/troubleshooting.md for more solutions."
      }
    ],
    "body": "MiniMax Easy Voice\n\nSimple text-to-speech skill powered by MiniMax Voice API. Converts any text into natural-sounding audio with customizable voice selection.\n\nUsage\n[Step 1] Preparation\n\nIMPORTANT: Before using this skill, always verify the environment:\n\npython check_environment.py\n\n\nIf API key is not set:\n\nexport MINIMAX_VOICE_API_KEY=\"your-api-key-here\"\n\n\nRequirements:\n\nPython 3.8+\nMINIMAX_VOICE_API_KEY environment variable (required)\nFFmpeg (optional, for audio merging/conversion)\n[Step 2] Generate speech audio from text\n\nConvert any text to speech in one command:\n\n# Default voice (male-qn-qingse)\npython mmvoice.py tts \"Hello, this is a test.\" -o test.mp3\n\n# Chinese text\npython mmvoice.py tts \"你好，这是一个测试。\" -o test_cn.mp3\n\n# Specify a different voice by \"-v voice_id\"\npython mmvoice.py tts \"Hello world\" -v female-shaonv -o hello.mp3\n\n# Specify output path\npython mmvoice.py tts \"Your text\" -o /path/to/output.mp3\n\n\nRequired parameters:\n\ntext: The text you want to convert to speech\n-o OUTPUT: Output audio file path (required)\n\nOptional parameters:\n\n-v VOICE_ID: Voice to use (default: male-qn-qingse)\nUsage Details\n\nText length limits:\n\nUp to 10,000 characters per request\nFor longer text, split into multiple requests and merge later\n\nPause insertion: Use <#x#> where x = pause duration in seconds\n\nExample: \"Hello<#1.5#>world\" = 1.5 second pause between words\nRange: 0.01 to 99.99 seconds\n\nEmotion matching: speech-2.8 models automatically match emotions to your text content\n\nVoice Selection\n\nChoose the right voice for your content by consulting the voice catalog:\n\n# List all available voices\npython mmvoice.py list-voices\n\n\nVoice catalog: reference/voice_catalog.md\n\nContains:\n\nAll available system voices (male, female)\nVoice characteristics and recommended use cases\nHow to select the right voice for your content\nAdvanced Options\nVoice Management\n\nList available voices:\n\npython mmvoice.py list-voices\n\n\nClone a voice from audio sample:\n\npython mmvoice.py clone audio_file.mp3 --voice-id my-custom-voice\n\n\nDesign a voice from description:\n\npython mmvoice.py design \"A warm, gentle female voice\" --voice-id designed-voice\n\nAudio Processing\n\nMerge multiple audio files:\n\npython mmvoice.py merge file1.mp3 file2.mp3 file3.mp3 -o combined.mp3\n\n\nConvert audio format:\n\npython mmvoice.py convert input.wav -o output.mp3 --format mp3\n\nReference Documents\n\nOpen these when needed for more details:\n\n|| Document | When to Use | ||----------|-------------| || reference/voice_catalog.md | Choosing a voice_id | || reference/getting-started.md | Environment setup | || reference/audio-guide.md | Audio processing | || reference/voice-guide.md | Voice cloning and design | || reference/troubleshooting.md | Common issues and solutions |\n\nTroubleshooting\n\nCommon issues:\n\nAPI key not set: Run export MINIMAX_VOICE_API_KEY=\"your-key\"\nFFmpeg missing: Install with brew install ffmpeg (macOS) or sudo apt install ffmpeg (Ubuntu)\nVoice not found: Use python mmvoice.py list-voices to see available voices\n\nRun environment check:\n\npython check_environment.py\n\n\nSee reference/troubleshooting.md for more solutions."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/BLUE-coconut/mm-easy-voice",
    "publisherUrl": "https://clawhub.ai/BLUE-coconut/mm-easy-voice",
    "owner": "BLUE-coconut",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/mm-easy-voice",
    "downloadUrl": "https://openagent3.xyz/downloads/mm-easy-voice",
    "agentUrl": "https://openagent3.xyz/skills/mm-easy-voice/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mm-easy-voice/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mm-easy-voice/agent.md"
  }
}