{
  "schemaVersion": "1.0",
  "item": {
    "slug": "audio-cog",
    "name": "audio-cog",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/nitishgargiitd/audio-cog",
    "canonicalUrl": "https://clawhub.ai/nitishgargiitd/audio-cog",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/audio-cog",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=audio-cog",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.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/audio-cog"
    },
    "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/audio-cog",
    "agentPageUrl": "https://openagent3.xyz/skills/audio-cog/agent",
    "manifestUrl": "https://openagent3.xyz/skills/audio-cog/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/audio-cog/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": "Audio Cog - AI Audio Generation Powered by CellCog",
        "body": "Create professional audio with AI - from voiceovers and narration to background music and sound design."
      },
      {
        "title": "Prerequisites",
        "body": "This skill requires the cellcog skill for SDK setup and API calls.\n\nclawhub install cellcog\n\nRead the cellcog skill first for SDK setup. This skill shows you what's possible.\n\nQuick pattern (v1.0+):\n\n# Fire-and-forget - returns immediately\nresult = client.create_chat(\n    prompt=\"[your audio request]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"audio-task\",\n    chat_mode=\"agent\"  # Agent mode is optimal for all audio tasks\n)\n# Daemon notifies you when complete - do NOT poll"
      },
      {
        "title": "Text-to-Speech / Voiceover",
        "body": "Convert text to natural-sounding speech:\n\nNarration: \"Generate a professional male voiceover for this product video script\"\nAudiobook Style: \"Create an engaging narration of this short story with emotional delivery\"\nPodcast Intros: \"Generate a warm, friendly podcast intro: 'Welcome to The Daily Tech...'\"\nE-Learning: \"Create clear, instructional voiceover for this training module\"\nIVR/Phone Systems: \"Generate professional phone menu prompts\""
      },
      {
        "title": "Available Voices",
        "body": "CellCog provides 8 high-quality voices with distinct characteristics:\n\nVoiceGenderBest ForCharacteristicscedarMaleProduct videos, announcementsWarm, resonant, authoritative, trustworthymarinFemaleProfessional content, tutorialsBright, articulate, emotionally agileballadMaleStorytelling, flowing narrativesSmooth, melodic, musical qualitycoralFemaleEnergetic content, adsVibrant, lively, dynamic, spiritedechoMaleThoughtful content, documentariesCalm, measured, deliberatesageFemaleEducational, knowledge contentWise, contemplative, reflectiveshimmerFemaleGentle content, wellnessSoft, gentle, soothing, approachableverseMaleCreative, artistic contentPoetic, rhythmic, expressive"
      },
      {
        "title": "Voice Recommendations by Use Case",
        "body": "For product videos and announcements:\n\nUse cedar (male) or marin (female) - both project confidence and professionalism.\n\nFor storytelling and audiobooks:\n\nUse ballad (male) or sage (female) - designed for engaging, flowing narratives.\n\nFor high-energy content:\n\nUse coral (female) - vibrant and dynamic, perfect for ads and exciting announcements.\n\nFor calm, educational content:\n\nUse echo (male) or shimmer (female) - measured pacing ideal for learning."
      },
      {
        "title": "Voice Style Customization",
        "body": "Beyond selecting a voice, you can fine-tune delivery with style instructions:\n\nAccent & dialect: American, British, Australian, Indian, etc.\nEmotional range: Excited, serious, warm, mysterious, dramatic\nPacing: Slow and deliberate, conversational, fast and energetic\nSpecial effects: Whispering, character impressions\n\nExample with style instructions:\n\n\"Generate voiceover using cedar voice with a warm, conversational tone. Speak at medium pace with slight enthusiasm when mentioning features. American accent.\""
      },
      {
        "title": "Music Generation",
        "body": "Create original background music and soundtracks:\n\nBackground Music: \"Create calm lo-fi background music for a study video, 2 minutes\"\nPodcast Music: \"Generate an upbeat intro jingle for a tech podcast, 15 seconds\"\nVideo Soundtracks: \"Create cinematic orchestral music for a product launch video\"\nAmbient/Mood: \"Generate peaceful ambient sounds for a meditation app\"\nGenre-Specific: \"Create energetic electronic music for a fitness video\""
      },
      {
        "title": "Music Specifications",
        "body": "ParameterOptionsDuration15 seconds to 5+ minutesGenreElectronic, rock, classical, jazz, ambient, lo-fi, cinematic, pop, hip-hopTempo60 BPM (slow) to 180+ BPM (fast)MoodUpbeat, calm, dramatic, mysterious, inspiring, melancholicInstrumentsPiano, guitar, synth, strings, drums, brass, etc."
      },
      {
        "title": "Music Licensing",
        "body": "All AI-generated music from CellCog is royalty-free and fully yours to use commercially.\n\nYou have complete rights to use the generated music for:\n\nYouTube videos (including monetized content)\nCommercial projects and advertisements\nPodcasts and streaming\nApps and games\nAny other commercial or personal use\n\nNo attribution required. No licensing fees. The music is generated uniquely for you."
      },
      {
        "title": "Audio Output Formats",
        "body": "FormatBest ForMP3Standard audio delivery, voiceovers, musicCombined with videoBackground music for video-cog outputs"
      },
      {
        "title": "Chat Mode for Audio",
        "body": "Use chat_mode=\"agent\" for all audio generation tasks.\n\nAudio generation—whether voiceovers, music, or sound design—executes efficiently in agent mode. CellCog's audio capabilities don't require multi-angle deliberation; they require precise execution, which agent mode excels at.\n\nThere's no scenario where agent team mode provides meaningfully better audio output. Save agent team for research and complex creative work that benefits from multiple reasoning passes."
      },
      {
        "title": "Example Audio Prompts",
        "body": "Professional voiceover with specific voice:\n\n\"Generate a professional voiceover using the marin voice for this script:\n'Introducing TaskFlow - the project management tool that actually works. With intelligent automation, seamless collaboration, and powerful analytics, TaskFlow helps teams do their best work.'\nStyle: Confident and friendly, medium pace. Suitable for a product launch video.\"\n\nPodcast intro with voice selection:\n\n\"Create a podcast intro voiceover using cedar voice:\n'Welcome to Future Forward, the podcast where we explore the technologies shaping tomorrow. I'm your host, and today we're diving into...'\nStyle: Warm and engaging, conversational tone. Also generate a 10-second upbeat intro music bed to go underneath.\"\n\nBackground music:\n\n\"Generate 2 minutes of calm, lo-fi hip-hop style background music. Should be chill and unobtrusive, good for studying or working. Include soft piano, mellow beats, and gentle vinyl crackle. 75 BPM.\"\n\nAudiobook narration:\n\n\"Create an audiobook-style narration using ballad voice for this passage:\n[passage text]\nStyle: Warm storytelling quality, measured pace with appropriate pauses for drama.\"\n\nCinematic music:\n\n\"Generate 90 seconds of cinematic orchestral music for a tech company's 'About Us' video. Start soft and inspiring, build to a confident crescendo, then resolve to a hopeful ending.\""
      },
      {
        "title": "Multi-Language Support",
        "body": "CellCog can generate speech in 50+ languages:\n\nEnglish (multiple accents)\nSpanish, French, German, Italian, Portuguese\nChinese (Mandarin, Cantonese)\nJapanese, Korean\nHindi, Arabic\nRussian, Polish, Dutch\nAnd many more\n\nSpecify the language in your prompt:\n\n\"Generate this text in Japanese with a native female speaker using shimmer voice: 'いらっしゃいませ...'\""
      },
      {
        "title": "Tips for Better Audio",
        "body": "Choose the right voice: Match the voice to your content type. Cedar/marin for professional, ballad/sage for storytelling, coral for energy.\n\n\nProvide the complete script: Don't say \"something about our product\" - write out exactly what should be said.\n\n\nInclude style instructions: \"Confident but warm\", \"slow and deliberate\", \"with slight excitement\" helps shape delivery.\n\n\nFor music: Specify duration, tempo (BPM if you know it), mood, and genre.\n\n\nPronunciation guidance: For names or technical terms, add hints: \"CellCog (pronounced SELL-kog)\"\n\n\nEmotional beats: For longer voiceovers, indicate tone shifts: \"[excited] And now for the big reveal... [serious] But there's a catch.\""
      }
    ],
    "body": "Audio Cog - AI Audio Generation Powered by CellCog\n\nCreate professional audio with AI - from voiceovers and narration to background music and sound design.\n\nPrerequisites\n\nThis skill requires the cellcog skill for SDK setup and API calls.\n\nclawhub install cellcog\n\n\nRead the cellcog skill first for SDK setup. This skill shows you what's possible.\n\nQuick pattern (v1.0+):\n\n# Fire-and-forget - returns immediately\nresult = client.create_chat(\n    prompt=\"[your audio request]\",\n    notify_session_key=\"agent:main:main\",\n    task_label=\"audio-task\",\n    chat_mode=\"agent\"  # Agent mode is optimal for all audio tasks\n)\n# Daemon notifies you when complete - do NOT poll\n\nWhat Audio You Can Create\nText-to-Speech / Voiceover\n\nConvert text to natural-sounding speech:\n\nNarration: \"Generate a professional male voiceover for this product video script\"\nAudiobook Style: \"Create an engaging narration of this short story with emotional delivery\"\nPodcast Intros: \"Generate a warm, friendly podcast intro: 'Welcome to The Daily Tech...'\"\nE-Learning: \"Create clear, instructional voiceover for this training module\"\nIVR/Phone Systems: \"Generate professional phone menu prompts\"\nAvailable Voices\n\nCellCog provides 8 high-quality voices with distinct characteristics:\n\nVoice\tGender\tBest For\tCharacteristics\ncedar\tMale\tProduct videos, announcements\tWarm, resonant, authoritative, trustworthy\nmarin\tFemale\tProfessional content, tutorials\tBright, articulate, emotionally agile\nballad\tMale\tStorytelling, flowing narratives\tSmooth, melodic, musical quality\ncoral\tFemale\tEnergetic content, ads\tVibrant, lively, dynamic, spirited\necho\tMale\tThoughtful content, documentaries\tCalm, measured, deliberate\nsage\tFemale\tEducational, knowledge content\tWise, contemplative, reflective\nshimmer\tFemale\tGentle content, wellness\tSoft, gentle, soothing, approachable\nverse\tMale\tCreative, artistic content\tPoetic, rhythmic, expressive\nVoice Recommendations by Use Case\n\nFor product videos and announcements:\n\nUse cedar (male) or marin (female) - both project confidence and professionalism.\n\nFor storytelling and audiobooks:\n\nUse ballad (male) or sage (female) - designed for engaging, flowing narratives.\n\nFor high-energy content:\n\nUse coral (female) - vibrant and dynamic, perfect for ads and exciting announcements.\n\nFor calm, educational content:\n\nUse echo (male) or shimmer (female) - measured pacing ideal for learning.\n\nVoice Style Customization\n\nBeyond selecting a voice, you can fine-tune delivery with style instructions:\n\nAccent & dialect: American, British, Australian, Indian, etc.\nEmotional range: Excited, serious, warm, mysterious, dramatic\nPacing: Slow and deliberate, conversational, fast and energetic\nSpecial effects: Whispering, character impressions\n\nExample with style instructions:\n\n\"Generate voiceover using cedar voice with a warm, conversational tone. Speak at medium pace with slight enthusiasm when mentioning features. American accent.\"\n\nMusic Generation\n\nCreate original background music and soundtracks:\n\nBackground Music: \"Create calm lo-fi background music for a study video, 2 minutes\"\nPodcast Music: \"Generate an upbeat intro jingle for a tech podcast, 15 seconds\"\nVideo Soundtracks: \"Create cinematic orchestral music for a product launch video\"\nAmbient/Mood: \"Generate peaceful ambient sounds for a meditation app\"\nGenre-Specific: \"Create energetic electronic music for a fitness video\"\nMusic Specifications\nParameter\tOptions\nDuration\t15 seconds to 5+ minutes\nGenre\tElectronic, rock, classical, jazz, ambient, lo-fi, cinematic, pop, hip-hop\nTempo\t60 BPM (slow) to 180+ BPM (fast)\nMood\tUpbeat, calm, dramatic, mysterious, inspiring, melancholic\nInstruments\tPiano, guitar, synth, strings, drums, brass, etc.\nMusic Licensing\n\nAll AI-generated music from CellCog is royalty-free and fully yours to use commercially.\n\nYou have complete rights to use the generated music for:\n\nYouTube videos (including monetized content)\nCommercial projects and advertisements\nPodcasts and streaming\nApps and games\nAny other commercial or personal use\n\nNo attribution required. No licensing fees. The music is generated uniquely for you.\n\nAudio Output Formats\nFormat\tBest For\nMP3\tStandard audio delivery, voiceovers, music\nCombined with video\tBackground music for video-cog outputs\nChat Mode for Audio\n\nUse chat_mode=\"agent\" for all audio generation tasks.\n\nAudio generation—whether voiceovers, music, or sound design—executes efficiently in agent mode. CellCog's audio capabilities don't require multi-angle deliberation; they require precise execution, which agent mode excels at.\n\nThere's no scenario where agent team mode provides meaningfully better audio output. Save agent team for research and complex creative work that benefits from multiple reasoning passes.\n\nExample Audio Prompts\n\nProfessional voiceover with specific voice:\n\n\"Generate a professional voiceover using the marin voice for this script:\n\n'Introducing TaskFlow - the project management tool that actually works. With intelligent automation, seamless collaboration, and powerful analytics, TaskFlow helps teams do their best work.'\n\nStyle: Confident and friendly, medium pace. Suitable for a product launch video.\"\n\nPodcast intro with voice selection:\n\n\"Create a podcast intro voiceover using cedar voice:\n\n'Welcome to Future Forward, the podcast where we explore the technologies shaping tomorrow. I'm your host, and today we're diving into...'\n\nStyle: Warm and engaging, conversational tone. Also generate a 10-second upbeat intro music bed to go underneath.\"\n\nBackground music:\n\n\"Generate 2 minutes of calm, lo-fi hip-hop style background music. Should be chill and unobtrusive, good for studying or working. Include soft piano, mellow beats, and gentle vinyl crackle. 75 BPM.\"\n\nAudiobook narration:\n\n\"Create an audiobook-style narration using ballad voice for this passage:\n\n[passage text]\n\nStyle: Warm storytelling quality, measured pace with appropriate pauses for drama.\"\n\nCinematic music:\n\n\"Generate 90 seconds of cinematic orchestral music for a tech company's 'About Us' video. Start soft and inspiring, build to a confident crescendo, then resolve to a hopeful ending.\"\n\nMulti-Language Support\n\nCellCog can generate speech in 50+ languages:\n\nEnglish (multiple accents)\nSpanish, French, German, Italian, Portuguese\nChinese (Mandarin, Cantonese)\nJapanese, Korean\nHindi, Arabic\nRussian, Polish, Dutch\nAnd many more\n\nSpecify the language in your prompt:\n\n\"Generate this text in Japanese with a native female speaker using shimmer voice: 'いらっしゃいませ...'\"\n\nTips for Better Audio\n\nChoose the right voice: Match the voice to your content type. Cedar/marin for professional, ballad/sage for storytelling, coral for energy.\n\nProvide the complete script: Don't say \"something about our product\" - write out exactly what should be said.\n\nInclude style instructions: \"Confident but warm\", \"slow and deliberate\", \"with slight excitement\" helps shape delivery.\n\nFor music: Specify duration, tempo (BPM if you know it), mood, and genre.\n\nPronunciation guidance: For names or technical terms, add hints: \"CellCog (pronounced SELL-kog)\"\n\nEmotional beats: For longer voiceovers, indicate tone shifts: \"[excited] And now for the big reveal... [serious] But there's a catch.\""
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/nitishgargiitd/audio-cog",
    "publisherUrl": "https://clawhub.ai/nitishgargiitd/audio-cog",
    "owner": "nitishgargiitd",
    "version": "1.0.3",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/audio-cog",
    "downloadUrl": "https://openagent3.xyz/downloads/audio-cog",
    "agentUrl": "https://openagent3.xyz/skills/audio-cog/agent",
    "manifestUrl": "https://openagent3.xyz/skills/audio-cog/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/audio-cog/agent.md"
  }
}