{
  "schemaVersion": "1.0",
  "item": {
    "slug": "audio",
    "name": "Audio",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/ivangdavila/audio",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/audio",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/audio",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=audio",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "commands.md",
      "loudness.md",
      "podcast.md",
      "transcription.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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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"
    },
    "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",
    "agentPageUrl": "https://openagent3.xyz/skills/audio/agent",
    "manifestUrl": "https://openagent3.xyz/skills/audio/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/audio/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": "Requirements",
        "body": "Required:\n\nffmpeg / ffprobe — core audio processing\n\nOptional (for advanced features):\n\nsox — additional noise reduction\nwhisper — local transcription (or use API)\ndemucs — stem separation"
      },
      {
        "title": "Quick Reference",
        "body": "SituationLoadFFmpeg commands by taskcommands.mdLoudness standards by platformloudness.mdPodcast production workflowpodcast.mdTranscription workflowtranscription.md"
      },
      {
        "title": "Core Capabilities",
        "body": "TaskMethodConvert formatsFFmpeg (-acodec)Remove noiseFFmpeg filters or SoXNormalize loudnessffmpeg-normalize or -af loudnormTranscribeWhisper → text, SRT, VTTSeparate stemsDemucs (vocals, drums, bass, other)"
      },
      {
        "title": "Execution Pattern",
        "body": "Clarify goal — What format? What loudness? What platform?\nAnalyze source — ffprobe for codec, sample rate, channels, duration\nProcess — FFmpeg/SoX for transformation\nVerify — Check output plays, meets specs, sounds correct\nDeliver — Provide file to user"
      },
      {
        "title": "Common Requests → Actions",
        "body": "User saysAgent does\"Convert to MP3\"-acodec libmp3lame -q:a 2\"Remove background noise\"Apply highpass/lowpass or dedicated denoiser\"Normalize for podcast\"-af loudnorm=I=-16:TP=-1.5:LRA=11\"Transcribe this\"Whisper → output SRT/VTT/TXT\"Extract audio from video\"-vn -acodec copy or re-encode\"Make it smaller\"Lower bitrate: -b:a 128k or -b:a 96k\"Speed up 1.5x\"-af atempo=1.5"
      },
      {
        "title": "Format Quick Reference",
        "body": "FormatUse CaseQualityWAVMaster, editingLosslessFLACArchive, audiophileLossless compressedMP3Universal sharingLossy, 128-320 kbpsAAC/M4AApple, podcastsLossy, efficientOGG/OpusWhatsApp, DiscordLossy, very efficient"
      },
      {
        "title": "Quality Defaults",
        "body": "Podcast: -16 LUFS (Spotify), -19 LUFS (Apple)\nMusic: -14 LUFS (Spotify), -16 LUFS (Apple Music)\nMP3 quality: VBR -q:a 2 (~190 kbps) or CBR -b:a 192k\nSample rate: 44.1kHz for music, 48kHz for video sync"
      },
      {
        "title": "Scope",
        "body": "This skill:\n\nProcesses audio files user explicitly provides\nRuns FFmpeg commands on user request\nDoes NOT access cloud services without user knowing\nDoes NOT store files persistently (user manages their files)"
      }
    ],
    "body": "Requirements\n\nRequired:\n\nffmpeg / ffprobe — core audio processing\n\nOptional (for advanced features):\n\nsox — additional noise reduction\nwhisper — local transcription (or use API)\ndemucs — stem separation\nQuick Reference\nSituation\tLoad\nFFmpeg commands by task\tcommands.md\nLoudness standards by platform\tloudness.md\nPodcast production workflow\tpodcast.md\nTranscription workflow\ttranscription.md\nCore Capabilities\nTask\tMethod\nConvert formats\tFFmpeg (-acodec)\nRemove noise\tFFmpeg filters or SoX\nNormalize loudness\tffmpeg-normalize or -af loudnorm\nTranscribe\tWhisper → text, SRT, VTT\nSeparate stems\tDemucs (vocals, drums, bass, other)\nExecution Pattern\nClarify goal — What format? What loudness? What platform?\nAnalyze source — ffprobe for codec, sample rate, channels, duration\nProcess — FFmpeg/SoX for transformation\nVerify — Check output plays, meets specs, sounds correct\nDeliver — Provide file to user\nCommon Requests → Actions\nUser says\tAgent does\n\"Convert to MP3\"\t-acodec libmp3lame -q:a 2\n\"Remove background noise\"\tApply highpass/lowpass or dedicated denoiser\n\"Normalize for podcast\"\t-af loudnorm=I=-16:TP=-1.5:LRA=11\n\"Transcribe this\"\tWhisper → output SRT/VTT/TXT\n\"Extract audio from video\"\t-vn -acodec copy or re-encode\n\"Make it smaller\"\tLower bitrate: -b:a 128k or -b:a 96k\n\"Speed up 1.5x\"\t-af atempo=1.5\nFormat Quick Reference\nFormat\tUse Case\tQuality\nWAV\tMaster, editing\tLossless\nFLAC\tArchive, audiophile\tLossless compressed\nMP3\tUniversal sharing\tLossy, 128-320 kbps\nAAC/M4A\tApple, podcasts\tLossy, efficient\nOGG/Opus\tWhatsApp, Discord\tLossy, very efficient\nQuality Defaults\nPodcast: -16 LUFS (Spotify), -19 LUFS (Apple)\nMusic: -14 LUFS (Spotify), -16 LUFS (Apple Music)\nMP3 quality: VBR -q:a 2 (~190 kbps) or CBR -b:a 192k\nSample rate: 44.1kHz for music, 48kHz for video sync\nScope\n\nThis skill:\n\nProcesses audio files user explicitly provides\nRuns FFmpeg commands on user request\nDoes NOT access cloud services without user knowing\nDoes NOT store files persistently (user manages their files)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/audio",
    "publisherUrl": "https://clawhub.ai/ivangdavila/audio",
    "owner": "ivangdavila",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/audio",
    "downloadUrl": "https://openagent3.xyz/downloads/audio",
    "agentUrl": "https://openagent3.xyz/skills/audio/agent",
    "manifestUrl": "https://openagent3.xyz/skills/audio/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/audio/agent.md"
  }
}