{
  "schemaVersion": "1.0",
  "item": {
    "slug": "local-voice",
    "name": "Local Voice (FluidAudio TTS/STT)",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/TrondW/local-voice",
    "canonicalUrl": "https://clawhub.ai/TrondW/local-voice",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/local-voice",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=local-voice",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/VOICES.md",
      "scripts/setup.sh",
      "scripts/stella-tts.sh",
      "sources/Package.swift",
      "sources/Sources/StellaVoice/main.swift"
    ],
    "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/local-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/local-voice",
    "agentPageUrl": "https://openagent3.xyz/skills/local-voice/agent",
    "manifestUrl": "https://openagent3.xyz/skills/local-voice/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/local-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": "Local Voice (FluidAudio TTS/STT)",
        "body": "Sub-second local voice AI for Apple Silicon Macs using FluidAudio's CoreML models."
      },
      {
        "title": "Features",
        "body": "TTS: Kokoro model with 54 voices, ~0.6-0.8s latency\nSTT: Parakeet TDT v3, ~0.2-0.3s latency, 25 languages\n100% local: No cloud, no cost, works offline\nNeural Engine: Runs on Apple's ANE for efficiency"
      },
      {
        "title": "Requirements",
        "body": "macOS 14+ on Apple Silicon (M1/M2/M3/M4)\nSwift 5.9+\nespeak-ng (for TTS phoneme fallback)"
      },
      {
        "title": "1. Install Dependencies",
        "body": "brew install espeak-ng"
      },
      {
        "title": "2. Build the Daemon",
        "body": "cd /path/to/skill/sources\nswift build -c release"
      },
      {
        "title": "3. Install Binary and Framework",
        "body": "mkdir -p ~/clawd/bin\ncp .build/release/StellaVoice ~/clawd/bin/\ncp -R .build/arm64-apple-macosx/release/ESpeakNG.framework ~/clawd/bin/\ninstall_name_tool -add_rpath @executable_path ~/clawd/bin/StellaVoice"
      },
      {
        "title": "4. Create LaunchAgent",
        "body": "cat > ~/Library/LaunchAgents/com.stella.tts.plist << 'EOF'\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<!DOCTYPE plist PUBLIC \"-//Apple//DTD PLIST 1.0//EN\" \"http://www.apple.com/DTDs/PropertyList-1.0.dtd\">\n<plist version=\"1.0\">\n<dict>\n    <key>Label</key>\n    <string>com.stella.tts</string>\n    <key>ProgramArguments</key>\n    <array>\n        <string>$HOME/clawd/bin/StellaVoice</string>\n    </array>\n    <key>RunAtLoad</key>\n    <true/>\n    <key>KeepAlive</key>\n    <true/>\n    <key>StandardOutPath</key>\n    <string>$HOME/.clawdbot/logs/stella-tts.log</string>\n    <key>StandardErrorPath</key>\n    <string>$HOME/.clawdbot/logs/stella-tts.err.log</string>\n</dict>\n</plist>\nEOF\n\nlaunchctl load ~/Library/LaunchAgents/com.stella.tts.plist"
      },
      {
        "title": "API Endpoints",
        "body": "The daemon listens on http://127.0.0.1:18790:"
      },
      {
        "title": "TTS - Text to Speech",
        "body": "# Simple text to WAV\ncurl -X POST http://127.0.0.1:18790/synthesize -d \"Hello world\" -o output.wav\n\n# With speed control (0.5-2.0)\ncurl -X POST \"http://127.0.0.1:18790/synthesize?speed=1.2\" -d \"Fast!\" -o output.wav\n\n# JSON endpoint\ncurl -X POST http://127.0.0.1:18790/synthesize/json \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"text\": \"Hello\", \"speed\": 1.0, \"deEss\": true}'"
      },
      {
        "title": "STT - Speech to Text",
        "body": "curl -X POST http://127.0.0.1:18790/transcribe \\\n  --data-binary @audio.wav \\\n  -H \"Content-Type: audio/wav\"\n# Returns: {\"text\": \"transcribed text\"}"
      },
      {
        "title": "Health Check",
        "body": "curl http://127.0.0.1:18790/health\n# Returns: ok"
      },
      {
        "title": "Voice Options",
        "body": "Default voice is af_sky. Change by modifying the source code.\n\nTop Kokoro voices (American female):\n\naf_heart (A grade) - warm, natural\naf_bella (A-) - expressive\naf_sky (C-) - clear, light\n\nAll 54 voices: See references/VOICES.md"
      },
      {
        "title": "Speed Control",
        "body": "speed=0.8 → Calm, relaxed\nspeed=1.0 → Natural pace\nspeed=1.2 → Energetic, upbeat"
      },
      {
        "title": "Punctuation (automatic)",
        "body": "! → Excited tone\n? → Rising intonation\n. → Neutral, falling\n... → Pauses"
      },
      {
        "title": "SSML Tags",
        "body": "<phoneme ph=\"kəkˈɔɹO\">Kokoro</phoneme>\n<sub alias=\"Doctor\">Dr.</sub>\n<say-as interpret-as=\"date\">2024-01-15</say-as>"
      },
      {
        "title": "Helper Script",
        "body": "See scripts/stella-tts.sh for a convenient wrapper:\n\nscripts/stella-tts.sh \"Hello world\" output.wav\nscripts/stella-tts.sh \"Hello world\" output.mp3  # Auto-converts"
      },
      {
        "title": "Integration Example",
        "body": "For voice assistants, update your voice proxy to use local endpoints:\n\n// STT\nconst response = await fetch('http://127.0.0.1:18790/transcribe', {\n    method: 'POST',\n    headers: { 'Content-Type': 'audio/wav' },\n    body: audioData\n});\nconst { text } = await response.json();\n\n// TTS\nconst audio = await fetch('http://127.0.0.1:18790/synthesize', {\n    method: 'POST',\n    body: textToSpeak\n});"
      },
      {
        "title": "Troubleshooting",
        "body": "Library not loaded (ESpeakNG)\n\nEnsure ESpeakNG.framework is in the same directory as the binary\nRun install_name_tool -add_rpath @executable_path /path/to/binary\n\nSlow first request\n\nFirst request loads models (~8-10s)\nSubsequent requests are sub-second\n\nx86 vs ARM\n\nMust build and run on ARM64 native (not Rosetta)\nCheck with uname -m (should show arm64)"
      },
      {
        "title": "Source Code",
        "body": "The daemon source is in sources/ directory. It's a Swift package using:\n\nFluidAudio (TTS + STT models)\nHummingbird (HTTP server)\n\nRebuild after modifying:\n\ncd sources && swift build -c release"
      }
    ],
    "body": "Local Voice (FluidAudio TTS/STT)\n\nSub-second local voice AI for Apple Silicon Macs using FluidAudio's CoreML models.\n\nFeatures\nTTS: Kokoro model with 54 voices, ~0.6-0.8s latency\nSTT: Parakeet TDT v3, ~0.2-0.3s latency, 25 languages\n100% local: No cloud, no cost, works offline\nNeural Engine: Runs on Apple's ANE for efficiency\nRequirements\nmacOS 14+ on Apple Silicon (M1/M2/M3/M4)\nSwift 5.9+\nespeak-ng (for TTS phoneme fallback)\nQuick Setup\n1. Install Dependencies\nbrew install espeak-ng\n\n2. Build the Daemon\ncd /path/to/skill/sources\nswift build -c release\n\n3. Install Binary and Framework\nmkdir -p ~/clawd/bin\ncp .build/release/StellaVoice ~/clawd/bin/\ncp -R .build/arm64-apple-macosx/release/ESpeakNG.framework ~/clawd/bin/\ninstall_name_tool -add_rpath @executable_path ~/clawd/bin/StellaVoice\n\n4. Create LaunchAgent\ncat > ~/Library/LaunchAgents/com.stella.tts.plist << 'EOF'\n<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<!DOCTYPE plist PUBLIC \"-//Apple//DTD PLIST 1.0//EN\" \"http://www.apple.com/DTDs/PropertyList-1.0.dtd\">\n<plist version=\"1.0\">\n<dict>\n    <key>Label</key>\n    <string>com.stella.tts</string>\n    <key>ProgramArguments</key>\n    <array>\n        <string>$HOME/clawd/bin/StellaVoice</string>\n    </array>\n    <key>RunAtLoad</key>\n    <true/>\n    <key>KeepAlive</key>\n    <true/>\n    <key>StandardOutPath</key>\n    <string>$HOME/.clawdbot/logs/stella-tts.log</string>\n    <key>StandardErrorPath</key>\n    <string>$HOME/.clawdbot/logs/stella-tts.err.log</string>\n</dict>\n</plist>\nEOF\n\nlaunchctl load ~/Library/LaunchAgents/com.stella.tts.plist\n\nAPI Endpoints\n\nThe daemon listens on http://127.0.0.1:18790:\n\nTTS - Text to Speech\n# Simple text to WAV\ncurl -X POST http://127.0.0.1:18790/synthesize -d \"Hello world\" -o output.wav\n\n# With speed control (0.5-2.0)\ncurl -X POST \"http://127.0.0.1:18790/synthesize?speed=1.2\" -d \"Fast!\" -o output.wav\n\n# JSON endpoint\ncurl -X POST http://127.0.0.1:18790/synthesize/json \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"text\": \"Hello\", \"speed\": 1.0, \"deEss\": true}'\n\nSTT - Speech to Text\ncurl -X POST http://127.0.0.1:18790/transcribe \\\n  --data-binary @audio.wav \\\n  -H \"Content-Type: audio/wav\"\n# Returns: {\"text\": \"transcribed text\"}\n\nHealth Check\ncurl http://127.0.0.1:18790/health\n# Returns: ok\n\nVoice Options\n\nDefault voice is af_sky. Change by modifying the source code.\n\nTop Kokoro voices (American female):\n\naf_heart (A grade) - warm, natural\naf_bella (A-) - expressive\naf_sky (C-) - clear, light\n\nAll 54 voices: See references/VOICES.md\n\nExpressiveness\nSpeed Control\nspeed=0.8 → Calm, relaxed\nspeed=1.0 → Natural pace\nspeed=1.2 → Energetic, upbeat\nPunctuation (automatic)\n! → Excited tone\n? → Rising intonation\n. → Neutral, falling\n... → Pauses\nSSML Tags\n<phoneme ph=\"kəkˈɔɹO\">Kokoro</phoneme>\n<sub alias=\"Doctor\">Dr.</sub>\n<say-as interpret-as=\"date\">2024-01-15</say-as>\n\nHelper Script\n\nSee scripts/stella-tts.sh for a convenient wrapper:\n\nscripts/stella-tts.sh \"Hello world\" output.wav\nscripts/stella-tts.sh \"Hello world\" output.mp3  # Auto-converts\n\nIntegration Example\n\nFor voice assistants, update your voice proxy to use local endpoints:\n\n// STT\nconst response = await fetch('http://127.0.0.1:18790/transcribe', {\n    method: 'POST',\n    headers: { 'Content-Type': 'audio/wav' },\n    body: audioData\n});\nconst { text } = await response.json();\n\n// TTS\nconst audio = await fetch('http://127.0.0.1:18790/synthesize', {\n    method: 'POST',\n    body: textToSpeak\n});\n\nTroubleshooting\n\nLibrary not loaded (ESpeakNG)\n\nEnsure ESpeakNG.framework is in the same directory as the binary\nRun install_name_tool -add_rpath @executable_path /path/to/binary\n\nSlow first request\n\nFirst request loads models (~8-10s)\nSubsequent requests are sub-second\n\nx86 vs ARM\n\nMust build and run on ARM64 native (not Rosetta)\nCheck with uname -m (should show arm64)\nSource Code\n\nThe daemon source is in sources/ directory. It's a Swift package using:\n\nFluidAudio (TTS + STT models)\nHummingbird (HTTP server)\n\nRebuild after modifying:\n\ncd sources && swift build -c release"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/TrondW/local-voice",
    "publisherUrl": "https://clawhub.ai/TrondW/local-voice",
    "owner": "TrondW",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/local-voice",
    "downloadUrl": "https://openagent3.xyz/downloads/local-voice",
    "agentUrl": "https://openagent3.xyz/skills/local-voice/agent",
    "manifestUrl": "https://openagent3.xyz/skills/local-voice/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/local-voice/agent.md"
  }
}