{
  "schemaVersion": "1.0",
  "item": {
    "slug": "mm-music-maker",
    "name": "mmMusicMaker",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/BLUE-coconut/mm-music-maker",
    "canonicalUrl": "https://clawhub.ai/BLUE-coconut/mm-music-maker",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/mm-music-maker",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mm-music-maker",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/utils_audio.py",
      "scripts/generate_music.py",
      "references/minimax_music_api.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": "2026-04-30T16:55:25.780Z",
      "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/mm-music-maker"
    },
    "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-music-maker",
    "agentPageUrl": "https://openagent3.xyz/skills/mm-music-maker/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mm-music-maker/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mm-music-maker/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 Music Maker",
        "body": "Use this skill to generate music with MiniMax's Music Generation API. All usage and outputs are designed for music-2.5 unless specified otherwise."
      },
      {
        "title": "Quick start",
        "body": "Set the API key:\n\nexport MINIMAX_MUSIC_API_KEY=\"your_api_key\"\n\nGenerate music from lyrics (and optional prompt):\n\npython scripts/generate_music.py \\\n  --lyrics \"[Verse]\\n...\\n[Chorus]\\n...\" \\\n  --prompt \"indie folk, melancholic, introspective\" \\\n  --output ./output.mp3"
      },
      {
        "title": "Script location",
        "body": "scripts/generate_music.py — main generator (lyrics + prompt → audio)\nscripts/utils_audio.py — hex decoding + save helpers"
      },
      {
        "title": "References",
        "body": "Read references/minimax_music_api.md for:\n\nEndpoint, auth header, payload schema\nRequired/optional fields\nOutput formats (hex/url) and constraints"
      },
      {
        "title": "Core Modes",
        "body": "This skill supports 3 generation modes:"
      },
      {
        "title": "1. Standard Song (with lyrics)",
        "body": "User provides or wants lyrics + music\nUse structured lyrics with prompt for style"
      },
      {
        "title": "2. Pure Music (Instrumental)",
        "body": "User requests: \"纯音乐\", \"纯音乐，无人声\", \"pure music\", \"instrumental\"\nNo lyrics, just instrumental arrangement\nSee \"Pure Music Generation\" section below"
      },
      {
        "title": "3. Melodic Chanting/Humming",
        "body": "User requests: \"哼唱\", \"吟唱\", \"humming\", \"chanting\"\nMusic with vocal syllables instead of full lyrics\nSee \"Melodic Chanting Generation\" section below"
      },
      {
        "title": "Notes",
        "body": "lyrics is required by the API.\nprompt is optional for music-2.5.\noutput_format defaults to hex (inline audio). Use url if you prefer a download URL.\nURLs expire (24h). Download immediately if using url."
      },
      {
        "title": "Prompt crafting (Important)",
        "body": "Core Principles: Use \"descriptions\" instead of \"commands\", keep it structured, clear, and parseable."
      },
      {
        "title": "Required Elements (Recommended)",
        "body": "Genre/Subgenre (with era or region)\nMood/Emotion (2-3 emotional descriptors)\nTempo/BPM (specify BPM if possible)\nKey Instruments (3-5 key instruments/timbres)\nVocals (vocal type, processing, or instrumental)\nUse case (purpose/scene)"
      },
      {
        "title": "Optional Enhancements",
        "body": "Structure (section structure)\nReferences (1-2 style references)\nAvoid/Negative (exclusions)"
      },
      {
        "title": "Prompt Templates",
        "body": "Basic Template (Beginner)\n\n[Genre], [Mood], [Tempo/BPM], [Key Instruments], [Vocal Style]\n\nStandard Template (Recommended)\n\nGenre: [Specific genre + era]\nMood: [2-3 descriptors]\nTempo: [BPM or speed]\nInstruments: [3-5 key instruments]\nVocals: [Type or instrumental only]\nUse case: [scene/usage]\nAvoid: [unwanted elements]\nReferences: [1-2 artists/songs]\n\nAdvanced Template (Production Brief)\n\nGenre: … | Era: …\nBPM: … | Key: …\nMood: ... (can include emotional arc, e.g., \"from restrained to explosive\")\nLead: …\nRhythm: …\nBass: …\nTexture: …\nVocals: …\nStructure: Intro / Verse / Chorus / Bridge / Outro\nAvoid: …\nReference: …"
      },
      {
        "title": "Structure Tags (in lyrics)",
        "body": "[Intro]\n[Verse]\n[Pre-Chorus]\n[Chorus]\n[Bridge]\n[Outro]\n[Instrumental]"
      },
      {
        "title": "Negative Prompt Examples",
        "body": "No vocals / Instrumental only\nAvoid autotune\nNo distorted guitars\nAvoid heavy reverb\nNo trap hi-hats"
      },
      {
        "title": "Common Issue Fixes",
        "body": "Style inaccurate: Add \"era + sub-genre + instrument anchors + reference artists\"\nRhythm wrong: Specify BPM + rhythm description (e.g., four-on-the-floor)\nIntro too generic: Write [Intro] in lyrics and describe the opening\nVocals off: Move Vocals to front of prompt and add negative constraints"
      },
      {
        "title": "Prompt Quality Checklist",
        "body": "Contains: Genre / Mood / BPM / Instruments / Vocals / Use case\nCheck for conflicts (e.g., \"very slow + high energy\")\nHas Avoid items to filter unwanted elements\nIs structured (avoid long prose paragraphs)"
      },
      {
        "title": "Pure Music Generation",
        "body": "Use this mode when user wants instrumental tracks without lyrics."
      },
      {
        "title": "Detection Keywords",
        "body": "纯音乐、纯音乐无人声、无人声\npure music、instrumental、no lyrics\n背景音乐、轻音乐、器乐\n无歌词"
      },
      {
        "title": "Prompt Format",
        "body": "pure music, [scene/style description], no lyrics"
      },
      {
        "title": "Lyrics Field",
        "body": "Use placeholder tags: [intro] [outro]"
      },
      {
        "title": "Important Notes",
        "body": "⚠️ Duration: Pure music tracks are typically shorter (1-2 minutes) because there's no lyrics to guide the musical progression."
      },
      {
        "title": "Pure Music Prompt Examples",
        "body": "#PromptScene1pure music, coffee shop, no lyrics咖啡馆氛围2pure music, rainy night, no lyrics雨夜3pure music, morning sunshine, no lyrics晨光4pure music, jazz bar, no lyrics爵士酒吧5pure music, city walk, no lyrics城市漫步6pure music, night drive, no lyrics夜间驾驶7pure music, piano solo, no lyrics钢琴独奏8pure music, lofi chill, no lyricsLo-Fi轻松9pure music, bookstore, no lyrics书店10pure music, cafe closing time, no lyrics咖啡馆打烊"
      },
      {
        "title": "CLI Examples",
        "body": "Generate pure music for coffee shop:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] [outro]\" \\\n  --prompt \"pure music, coffee shop, no lyrics\" \\\n  --output ./coffee_shop.mp3\n\nGenerate rainy night atmosphere:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] [outro]\" \\\n  --prompt \"pure music, rainy night, no lyrics\" \\\n  --output ./rainy_night.mp3\n\nGenerate piano solo:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] [outro]\" \\\n  --prompt \"pure music, piano solo, no lyrics\" \\\n  --output ./piano_solo.mp3"
      },
      {
        "title": "Melodic Chanting/Humming Generation",
        "body": "Use this mode when user wants music with vocal syllables instead of full lyrics (humming, chanting)."
      },
      {
        "title": "Detection Keywords",
        "body": "Humming, chanting, vocalizing\nhumming、chanting\nHealing, vocal accompaniment\nMelodic\nHarmony, ooh ah la"
      },
      {
        "title": "Prompt Format",
        "body": "pure music, [风格/场景描述], no lyrics"
      },
      {
        "title": "Lyrics Field (Syllable Patterns)",
        "body": "Use vocal syllables instead of words:\n\nSyllable PatternVibeah, ah, ah, ah...柔和吟唱la, la, la, la...旋律哼唱mmm, mmm, mmm...治愈系哼鸣ooh, ooh, ooh...空灵吟唱hum, hum, hum...持续哼唱"
      },
      {
        "title": "Lyrics Structure Template",
        "body": "[intro] [verse] [chorus] [verse] [outro]\n\nReplace sections with chosen syllables."
      },
      {
        "title": "Chanting Prompt Examples",
        "body": "ScenePromptLyricsHealingpure music, healing, relaxing, no lyrics[intro] mmm, mmm, mmm... [verse] mmm, mmm, mmm... [outro]Meditationpure music, meditation, calming, no lyrics[intro] ooh, ooh, ooh... [verse] ooh, ooh, ooh... [outro]Happypure music, happy, uplifting, no lyrics[intro] la, la, la, la... [chorus] la, la, la, la... [outro]Mysticalpure music, mystical, ethereal, no lyrics[intro] ah, ah, ah... [verse] ah, ah, ah... [outro]"
      },
      {
        "title": "CLI Examples",
        "body": "Generate healing chant music:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] mmm, mmm, mmm... [verse] mmm, mmm, mmm... [chorus] mmm, mmm, mmm... [outro]\" \\\n  --prompt \"pure music, healing, relaxing, no lyrics\" \\\n  --output ./healing_chant.mp3\n\nGenerate meditation chant:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] ooh, ooh, ooh... [verse] ooh, ooh, ooh... [outro]\" \\\n  --prompt \"pure music, meditation, calming, no lyrics\" \\\n  --output ./meditation.mp3\n\nGenerate happy humming:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] la, la, la... [verse] la, la, la... [chorus] la, la, la... [outro]\" \\\n  --prompt \"pure music, happy, uplifting, no lyrics\" \\\n  --output ./happy_humming.mp3"
      },
      {
        "title": "Mode Detection Logic",
        "body": "When user requests music, detect the mode:\n\nStandard Song → User provides lyrics OR asks for \"song with lyrics\"\nPure Music → Keywords: \"纯音乐\", \"pure music\", \"instrumental\", \"no lyrics\", \"无人声\"\nChanting/Humming → Keywords: \"哼唱\", \"吟唱\", \"humming\", \"chanting\", \"治愈系\""
      },
      {
        "title": "Decision Flow",
        "body": "User Request\n    ↓\nContains \"纯音乐\"/\"pure music\"/\"instrumental\"?\n    ├─ Yes → Is \"哼唱\"/\"humming\" also mentioned?\n    │   ├─ Yes → Melodic Chanting Mode\n    │   └─ No → Pure Music Mode\n    └─ No → Standard Song Mode (requires lyrics)"
      },
      {
        "title": "Recommended CLI patterns",
        "body": "Generate MP3 (hex response → file):\n\npython scripts/generate_music.py \\\n  --lyrics \"[Intro]\\n...\" \\\n  --prompt \"cinematic, uplifting\" \\\n  --output ./music.mp3 \\\n  --format mp3 \\\n  --bitrate 256000 \\\n  --sample-rate 44100\n\nGenerate with structured prompt fields (auto-build):\n\npython scripts/generate_music.py \\\n  --lyrics \"[Verse]\\n...\" \\\n  --genre \"1980s synthwave\" \\\n  --mood \"nostalgic, energetic\" \\\n  --bpm 120 \\\n  --instruments \"analog synths, drum machine, bass guitar\" \\\n  --vocals \"female vocals\" \\\n  --use-case \"retro game trailer\" \\\n  --avoid \"no acoustic guitar\" \\\n  --references \"The Midnight, FM-84\" \\\n  --output ./music.mp3\n\nGenerate and download from URL:\n\npython scripts/generate_music.py \\\n  --lyrics \"[Verse]\\n...\" \\\n  --prompt \"lofi, rainy night\" \\\n  --output ./music.mp3 \\\n  --output-format url \\\n  --download"
      },
      {
        "title": "API Reference",
        "body": "For detailed API documentation (endpoints, authentication, request/response formats), see:\n\nreferences/minimax_music_api.md\n\nKey points for all modes:\n\nEndpoint: POST https://api.minimaxi.com/v1/music_generation\nAuth: Authorization: Bearer <token>\nModel: music-2.5\nlyrics: Required field - use [intro] [outro] for pure music, or syllable patterns for chanting"
      },
      {
        "title": "Quick API Payload Examples",
        "body": "Standard Song:\n\n{\n  \"model\": \"music-2.5\",\n  \"prompt\": \"indie folk, melancholic, introspective\",\n  \"lyrics\": \"[verse]\\n...\\n[chorus]\\n...\"\n}\n\nPure Music:\n\n{\n  \"model\": \"music-2.5\",\n  \"prompt\": \"pure music, coffee shop, no lyrics\",\n  \"lyrics\": \"[intro] [outro]\"\n}\n\nMelodic Chanting:\n\n{\n  \"model\": \"music-2.5\",\n  \"prompt\": \"pure music, healing, relaxing, no lyrics\",\n  \"lyrics\": \"[intro] mmm, mmm, mmm... [verse] mmm, mmm, mmm... [outro]\"\n}"
      },
      {
        "title": "Response Format",
        "body": "data.audio: hex string (default) or URL (valid 24 hours)\ndata.status: generation status\nextra_info: duration, sample rate, channels, bitrate, size\nbase_resp.status_code: 0 on success"
      }
    ],
    "body": "MiniMax Music Maker\n\nUse this skill to generate music with MiniMax's Music Generation API. All usage and outputs are designed for music-2.5 unless specified otherwise.\n\nQuick start\nSet the API key:\nexport MINIMAX_MUSIC_API_KEY=\"your_api_key\"\n\nGenerate music from lyrics (and optional prompt):\npython scripts/generate_music.py \\\n  --lyrics \"[Verse]\\n...\\n[Chorus]\\n...\" \\\n  --prompt \"indie folk, melancholic, introspective\" \\\n  --output ./output.mp3\n\nScript location\nscripts/generate_music.py — main generator (lyrics + prompt → audio)\nscripts/utils_audio.py — hex decoding + save helpers\nReferences\n\nRead references/minimax_music_api.md for:\n\nEndpoint, auth header, payload schema\nRequired/optional fields\nOutput formats (hex/url) and constraints\nCore Modes\n\nThis skill supports 3 generation modes:\n\n1. Standard Song (with lyrics)\nUser provides or wants lyrics + music\nUse structured lyrics with prompt for style\n2. Pure Music (Instrumental)\nUser requests: \"纯音乐\", \"纯音乐，无人声\", \"pure music\", \"instrumental\"\nNo lyrics, just instrumental arrangement\nSee \"Pure Music Generation\" section below\n3. Melodic Chanting/Humming\nUser requests: \"哼唱\", \"吟唱\", \"humming\", \"chanting\"\nMusic with vocal syllables instead of full lyrics\nSee \"Melodic Chanting Generation\" section below\nNotes\nlyrics is required by the API.\nprompt is optional for music-2.5.\noutput_format defaults to hex (inline audio). Use url if you prefer a download URL.\nURLs expire (24h). Download immediately if using url.\nPrompt crafting (Important)\n\nCore Principles: Use \"descriptions\" instead of \"commands\", keep it structured, clear, and parseable.\n\nRequired Elements (Recommended)\nGenre/Subgenre (with era or region)\nMood/Emotion (2-3 emotional descriptors)\nTempo/BPM (specify BPM if possible)\nKey Instruments (3-5 key instruments/timbres)\nVocals (vocal type, processing, or instrumental)\nUse case (purpose/scene)\nOptional Enhancements\nStructure (section structure)\nReferences (1-2 style references)\nAvoid/Negative (exclusions)\nPrompt Templates\n\nBasic Template (Beginner)\n\n[Genre], [Mood], [Tempo/BPM], [Key Instruments], [Vocal Style]\n\n\nStandard Template (Recommended)\n\nGenre: [Specific genre + era]\nMood: [2-3 descriptors]\nTempo: [BPM or speed]\nInstruments: [3-5 key instruments]\nVocals: [Type or instrumental only]\nUse case: [scene/usage]\nAvoid: [unwanted elements]\nReferences: [1-2 artists/songs]\n\n\nAdvanced Template (Production Brief)\n\nGenre: … | Era: …\nBPM: … | Key: …\nMood: ... (can include emotional arc, e.g., \"from restrained to explosive\")\nLead: …\nRhythm: …\nBass: …\nTexture: …\nVocals: …\nStructure: Intro / Verse / Chorus / Bridge / Outro\nAvoid: …\nReference: …\n\nStructure Tags (in lyrics)\n[Intro]\n[Verse]\n[Pre-Chorus]\n[Chorus]\n[Bridge]\n[Outro]\n[Instrumental]\n\nNegative Prompt Examples\nNo vocals / Instrumental only\nAvoid autotune\nNo distorted guitars\nAvoid heavy reverb\nNo trap hi-hats\nCommon Issue Fixes\nStyle inaccurate: Add \"era + sub-genre + instrument anchors + reference artists\"\nRhythm wrong: Specify BPM + rhythm description (e.g., four-on-the-floor)\nIntro too generic: Write [Intro] in lyrics and describe the opening\nVocals off: Move Vocals to front of prompt and add negative constraints\nPrompt Quality Checklist\nContains: Genre / Mood / BPM / Instruments / Vocals / Use case\nCheck for conflicts (e.g., \"very slow + high energy\")\nHas Avoid items to filter unwanted elements\nIs structured (avoid long prose paragraphs)\nPure Music Generation\n\nUse this mode when user wants instrumental tracks without lyrics.\n\nDetection Keywords\n纯音乐、纯音乐无人声、无人声\npure music、instrumental、no lyrics\n背景音乐、轻音乐、器乐\n无歌词\nPrompt Format\npure music, [scene/style description], no lyrics\n\nLyrics Field\n\nUse placeholder tags: [intro] [outro]\n\nImportant Notes\n\n⚠️ Duration: Pure music tracks are typically shorter (1-2 minutes) because there's no lyrics to guide the musical progression.\n\nPure Music Prompt Examples\n#\tPrompt\tScene\n1\tpure music, coffee shop, no lyrics\t咖啡馆氛围\n2\tpure music, rainy night, no lyrics\t雨夜\n3\tpure music, morning sunshine, no lyrics\t晨光\n4\tpure music, jazz bar, no lyrics\t爵士酒吧\n5\tpure music, city walk, no lyrics\t城市漫步\n6\tpure music, night drive, no lyrics\t夜间驾驶\n7\tpure music, piano solo, no lyrics\t钢琴独奏\n8\tpure music, lofi chill, no lyrics\tLo-Fi轻松\n9\tpure music, bookstore, no lyrics\t书店\n10\tpure music, cafe closing time, no lyrics\t咖啡馆打烊\nCLI Examples\n\nGenerate pure music for coffee shop:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] [outro]\" \\\n  --prompt \"pure music, coffee shop, no lyrics\" \\\n  --output ./coffee_shop.mp3\n\n\nGenerate rainy night atmosphere:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] [outro]\" \\\n  --prompt \"pure music, rainy night, no lyrics\" \\\n  --output ./rainy_night.mp3\n\n\nGenerate piano solo:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] [outro]\" \\\n  --prompt \"pure music, piano solo, no lyrics\" \\\n  --output ./piano_solo.mp3\n\nMelodic Chanting/Humming Generation\n\nUse this mode when user wants music with vocal syllables instead of full lyrics (humming, chanting).\n\nDetection Keywords\nHumming, chanting, vocalizing\nhumming、chanting\nHealing, vocal accompaniment\nMelodic\nHarmony, ooh ah la\nPrompt Format\npure music, [风格/场景描述], no lyrics\n\nLyrics Field (Syllable Patterns)\n\nUse vocal syllables instead of words:\n\nSyllable Pattern\tVibe\nah, ah, ah, ah...\t柔和吟唱\nla, la, la, la...\t旋律哼唱\nmmm, mmm, mmm...\t治愈系哼鸣\nooh, ooh, ooh...\t空灵吟唱\nhum, hum, hum...\t持续哼唱\nLyrics Structure Template\n[intro] [verse] [chorus] [verse] [outro]\n\n\nReplace sections with chosen syllables.\n\nChanting Prompt Examples\nScene\tPrompt\tLyrics\nHealing\tpure music, healing, relaxing, no lyrics\t[intro] mmm, mmm, mmm... [verse] mmm, mmm, mmm... [outro]\nMeditation\tpure music, meditation, calming, no lyrics\t[intro] ooh, ooh, ooh... [verse] ooh, ooh, ooh... [outro]\nHappy\tpure music, happy, uplifting, no lyrics\t[intro] la, la, la, la... [chorus] la, la, la, la... [outro]\nMystical\tpure music, mystical, ethereal, no lyrics\t[intro] ah, ah, ah... [verse] ah, ah, ah... [outro]\nCLI Examples\n\nGenerate healing chant music:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] mmm, mmm, mmm... [verse] mmm, mmm, mmm... [chorus] mmm, mmm, mmm... [outro]\" \\\n  --prompt \"pure music, healing, relaxing, no lyrics\" \\\n  --output ./healing_chant.mp3\n\n\nGenerate meditation chant:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] ooh, ooh, ooh... [verse] ooh, ooh, ooh... [outro]\" \\\n  --prompt \"pure music, meditation, calming, no lyrics\" \\\n  --output ./meditation.mp3\n\n\nGenerate happy humming:\n\npython scripts/generate_music.py \\\n  --lyrics \"[intro] la, la, la... [verse] la, la, la... [chorus] la, la, la... [outro]\" \\\n  --prompt \"pure music, happy, uplifting, no lyrics\" \\\n  --output ./happy_humming.mp3\n\nMode Detection Logic\n\nWhen user requests music, detect the mode:\n\nStandard Song → User provides lyrics OR asks for \"song with lyrics\"\nPure Music → Keywords: \"纯音乐\", \"pure music\", \"instrumental\", \"no lyrics\", \"无人声\"\nChanting/Humming → Keywords: \"哼唱\", \"吟唱\", \"humming\", \"chanting\", \"治愈系\"\nDecision Flow\nUser Request\n    ↓\nContains \"纯音乐\"/\"pure music\"/\"instrumental\"?\n    ├─ Yes → Is \"哼唱\"/\"humming\" also mentioned?\n    │   ├─ Yes → Melodic Chanting Mode\n    │   └─ No → Pure Music Mode\n    └─ No → Standard Song Mode (requires lyrics)\n\nRecommended CLI patterns\n\nGenerate MP3 (hex response → file):\n\npython scripts/generate_music.py \\\n  --lyrics \"[Intro]\\n...\" \\\n  --prompt \"cinematic, uplifting\" \\\n  --output ./music.mp3 \\\n  --format mp3 \\\n  --bitrate 256000 \\\n  --sample-rate 44100\n\n\nGenerate with structured prompt fields (auto-build):\n\npython scripts/generate_music.py \\\n  --lyrics \"[Verse]\\n...\" \\\n  --genre \"1980s synthwave\" \\\n  --mood \"nostalgic, energetic\" \\\n  --bpm 120 \\\n  --instruments \"analog synths, drum machine, bass guitar\" \\\n  --vocals \"female vocals\" \\\n  --use-case \"retro game trailer\" \\\n  --avoid \"no acoustic guitar\" \\\n  --references \"The Midnight, FM-84\" \\\n  --output ./music.mp3\n\n\nGenerate and download from URL:\n\npython scripts/generate_music.py \\\n  --lyrics \"[Verse]\\n...\" \\\n  --prompt \"lofi, rainy night\" \\\n  --output ./music.mp3 \\\n  --output-format url \\\n  --download\n\nAPI Reference\n\nFor detailed API documentation (endpoints, authentication, request/response formats), see:\n\nreferences/minimax_music_api.md\n\nKey points for all modes:\n\nEndpoint: POST https://api.minimaxi.com/v1/music_generation\nAuth: Authorization: Bearer <token>\nModel: music-2.5\nlyrics: Required field - use [intro] [outro] for pure music, or syllable patterns for chanting\nQuick API Payload Examples\n\nStandard Song:\n\n{\n  \"model\": \"music-2.5\",\n  \"prompt\": \"indie folk, melancholic, introspective\",\n  \"lyrics\": \"[verse]\\n...\\n[chorus]\\n...\"\n}\n\n\nPure Music:\n\n{\n  \"model\": \"music-2.5\",\n  \"prompt\": \"pure music, coffee shop, no lyrics\",\n  \"lyrics\": \"[intro] [outro]\"\n}\n\n\nMelodic Chanting:\n\n{\n  \"model\": \"music-2.5\",\n  \"prompt\": \"pure music, healing, relaxing, no lyrics\",\n  \"lyrics\": \"[intro] mmm, mmm, mmm... [verse] mmm, mmm, mmm... [outro]\"\n}\n\nResponse Format\ndata.audio: hex string (default) or URL (valid 24 hours)\ndata.status: generation status\nextra_info: duration, sample rate, channels, bitrate, size\nbase_resp.status_code: 0 on success"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/BLUE-coconut/mm-music-maker",
    "publisherUrl": "https://clawhub.ai/BLUE-coconut/mm-music-maker",
    "owner": "BLUE-coconut",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/mm-music-maker",
    "downloadUrl": "https://openagent3.xyz/downloads/mm-music-maker",
    "agentUrl": "https://openagent3.xyz/skills/mm-music-maker/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mm-music-maker/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mm-music-maker/agent.md"
  }
}