{
  "schemaVersion": "1.0",
  "item": {
    "slug": "whisper-mlx-local",
    "name": "Local Whisper",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ImpKind/whisper-mlx-local",
    "canonicalUrl": "https://clawhub.ai/ImpKind/whisper-mlx-local",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/whisper-mlx-local",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=whisper-mlx-local",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "requirements.txt",
      "scripts/daemon.py",
      "scripts/transcribe.sh",
      "scripts/transcribe_large.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",
      "slug": "whisper-mlx-local",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-05T03:30:50.332Z",
      "expiresAt": "2026-05-12T03:30:50.332Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=whisper-mlx-local",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=whisper-mlx-local",
        "contentDisposition": "attachment; filename=\"whisper-mlx-local-1.5.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "whisper-mlx-local"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/whisper-mlx-local"
    },
    "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/whisper-mlx-local",
    "agentPageUrl": "https://openagent3.xyz/skills/whisper-mlx-local/agent",
    "manifestUrl": "https://openagent3.xyz/skills/whisper-mlx-local/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/whisper-mlx-local/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": "Local Whisper",
        "body": "Transcribe voice messages for free on Telegram and WhatsApp. No API keys. No costs. Runs on your Mac."
      },
      {
        "title": "The Problem",
        "body": "Voice transcription APIs cost money:\n\nOpenAI Whisper: $0.006/minute\nGroq: $0.001/minute\nAssemblyAI: $0.01/minute\n\nIf you transcribe a lot of Telegram voice messages, it adds up."
      },
      {
        "title": "The Solution",
        "body": "This skill runs Whisper locally on your Mac. Same quality, zero cost.\n\n✅ Free forever\n✅ Private (audio never leaves your Mac)\n✅ Fast (~1 second per message)\n✅ Works offline"
      },
      {
        "title": "⚠️ Important Notes",
        "body": "First run downloads ~1.5GB model — be patient, this only happens once\nFirst transcription is slow — model loads into memory (~10-30 seconds), then it's instant\nAlready using OpenAI API for transcription? Replace your existing tools.media.audio config with the one below"
      },
      {
        "title": "1. Install dependencies",
        "body": "pip3 install -r requirements.txt"
      },
      {
        "title": "2. Start the daemon",
        "body": "python3 scripts/daemon.py\n\nFirst run will download the Whisper model (~1.5GB). Wait for \"Ready\" message."
      },
      {
        "title": "3. Add to OpenClaw config",
        "body": "Add this to your ~/.openclaw/openclaw.json:\n\n{\n  \"tools\": {\n    \"media\": {\n      \"audio\": {\n        \"enabled\": true,\n        \"models\": [\n          {\n            \"type\": \"cli\",\n            \"command\": \"~/.openclaw/workspace/skills/local-whisper/scripts/transcribe.sh\",\n            \"args\": [\"{{MediaPath}}\"],\n            \"timeoutSeconds\": 60\n          }\n        ]\n      }\n    }\n  }\n}"
      },
      {
        "title": "4. Restart gateway",
        "body": "openclaw gateway restart\n\nNow voice messages from Telegram, WhatsApp, etc. will be transcribed locally for free!"
      },
      {
        "title": "Manual test",
        "body": "./scripts/transcribe.sh voice_message.ogg"
      },
      {
        "title": "Use Case: Telegram Voice Messages",
        "body": "Instead of paying for OpenAI API to transcribe incoming voice messages, point OpenClaw to this local daemon. Free transcription forever."
      },
      {
        "title": "Auto-Start on Login",
        "body": "cp com.local-whisper.plist ~/Library/LaunchAgents/\nlaunchctl load ~/Library/LaunchAgents/com.local-whisper.plist"
      },
      {
        "title": "API",
        "body": "Daemon runs at localhost:8787:\n\ncurl -X POST http://localhost:8787/transcribe -F \"file=@audio.ogg\"\n# {\"text\": \"Hello world\", \"language\": \"en\"}"
      },
      {
        "title": "Translation",
        "body": "Any language → English:\n\n./scripts/transcribe.sh spanish_audio.ogg --translate"
      },
      {
        "title": "Requirements",
        "body": "macOS with Apple Silicon (M1/M2/M3/M4)\nPython 3.9+"
      },
      {
        "title": "License",
        "body": "MIT"
      }
    ],
    "body": "Local Whisper\n\nTranscribe voice messages for free on Telegram and WhatsApp. No API keys. No costs. Runs on your Mac.\n\nThe Problem\n\nVoice transcription APIs cost money:\n\nOpenAI Whisper: $0.006/minute\nGroq: $0.001/minute\nAssemblyAI: $0.01/minute\n\nIf you transcribe a lot of Telegram voice messages, it adds up.\n\nThe Solution\n\nThis skill runs Whisper locally on your Mac. Same quality, zero cost.\n\n✅ Free forever\n✅ Private (audio never leaves your Mac)\n✅ Fast (~1 second per message)\n✅ Works offline\n⚠️ Important Notes\nFirst run downloads ~1.5GB model — be patient, this only happens once\nFirst transcription is slow — model loads into memory (~10-30 seconds), then it's instant\nAlready using OpenAI API for transcription? Replace your existing tools.media.audio config with the one below\nQuick Start\n1. Install dependencies\npip3 install -r requirements.txt\n\n2. Start the daemon\npython3 scripts/daemon.py\n\n\nFirst run will download the Whisper model (~1.5GB). Wait for \"Ready\" message.\n\n3. Add to OpenClaw config\n\nAdd this to your ~/.openclaw/openclaw.json:\n\n{\n  \"tools\": {\n    \"media\": {\n      \"audio\": {\n        \"enabled\": true,\n        \"models\": [\n          {\n            \"type\": \"cli\",\n            \"command\": \"~/.openclaw/workspace/skills/local-whisper/scripts/transcribe.sh\",\n            \"args\": [\"{{MediaPath}}\"],\n            \"timeoutSeconds\": 60\n          }\n        ]\n      }\n    }\n  }\n}\n\n4. Restart gateway\nopenclaw gateway restart\n\n\nNow voice messages from Telegram, WhatsApp, etc. will be transcribed locally for free!\n\nManual test\n./scripts/transcribe.sh voice_message.ogg\n\nUse Case: Telegram Voice Messages\n\nInstead of paying for OpenAI API to transcribe incoming voice messages, point OpenClaw to this local daemon. Free transcription forever.\n\nAuto-Start on Login\ncp com.local-whisper.plist ~/Library/LaunchAgents/\nlaunchctl load ~/Library/LaunchAgents/com.local-whisper.plist\n\nAPI\n\nDaemon runs at localhost:8787:\n\ncurl -X POST http://localhost:8787/transcribe -F \"file=@audio.ogg\"\n# {\"text\": \"Hello world\", \"language\": \"en\"}\n\nTranslation\n\nAny language → English:\n\n./scripts/transcribe.sh spanish_audio.ogg --translate\n\nRequirements\nmacOS with Apple Silicon (M1/M2/M3/M4)\nPython 3.9+\nLicense\n\nMIT"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ImpKind/whisper-mlx-local",
    "publisherUrl": "https://clawhub.ai/ImpKind/whisper-mlx-local",
    "owner": "ImpKind",
    "version": "1.5.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/whisper-mlx-local",
    "downloadUrl": "https://openagent3.xyz/downloads/whisper-mlx-local",
    "agentUrl": "https://openagent3.xyz/skills/whisper-mlx-local/agent",
    "manifestUrl": "https://openagent3.xyz/skills/whisper-mlx-local/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/whisper-mlx-local/agent.md"
  }
}