{
  "schemaVersion": "1.0",
  "item": {
    "slug": "local-piper-tts-multilang-secure",
    "name": "Truly Local Piper Multilang TTS (secure)",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/szafranski/local-piper-tts-multilang-secure",
    "canonicalUrl": "https://clawhub.ai/szafranski/local-piper-tts-multilang-secure",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/local-piper-tts-multilang-secure",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=local-piper-tts-multilang-secure",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "_meta.json",
      "package.json",
      "index.js",
      "SKILL.md",
      "README.md",
      "piper-tts.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",
      "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-piper-tts-multilang-secure"
    },
    "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-piper-tts-multilang-secure",
    "agentPageUrl": "https://openagent3.xyz/skills/local-piper-tts-multilang-secure/agent",
    "manifestUrl": "https://openagent3.xyz/skills/local-piper-tts-multilang-secure/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/local-piper-tts-multilang-secure/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": "Description",
        "body": "Local (offline) text-to-speech via Piper.\n\nPurpose: generate audio files (OGG/Opus by default) from text, fully offline.\nNo sending is performed by the skill — sending is handled by the agent after the file is ready."
      },
      {
        "title": "Features",
        "body": "Fully offline (no API keys)\nSelf-contained setup via setup() — installs Piper into an isolated venv, no system-wide changes\nAutomatic language detection for 20+ languages with English as default\nPer-call voice selection via voice parameter\nOn-demand voice download via downloadVoices() — no models bundled, choose what you need\nVoice removal via removeVoice() — clean up voices you no longer want\nExtensible: add any language by installing a Piper .onnx model\nWrites outputs into OpenClaw workspace"
      },
      {
        "title": "First-run flow — full agent procedure",
        "body": "Follow this sequence exactly when the user asks to use TTS for the first time in a setup context."
      },
      {
        "title": "Step 1 — check status",
        "body": "const s = await status();"
      },
      {
        "title": "Step 2 — install Piper if needed",
        "body": "If s.stage is not-setup or no-piper:\n\nTell the user: \"To use local TTS I need to install piper-tts into the skill's venv (~30 seconds, one-time). OK to proceed?\"\nWait for confirmation, then call setup().\nIf setup returns a step containing \"WARNING: espeak-ng not found\", relay the warning and install instructions to the user.\nCall status() again after setup completes."
      },
      {
        "title": "Step 3 — offer voice download if no models present",
        "body": "If s.stage is no-model (Piper installed but no .onnx files):\n\n3a. Offer English defaults:\nExplain that two English voices are available as defaults (~65 MB each):\n\nen_US-ryan-medium — male, American\nen_US-amy-medium — female, American\n\nAsk which they want, or both: \"Which English voice(s) should I download? Ryan (male), Amy (female), or both?\"\n\n3b. Ask about other languages:\nAfter the English choice, ask: \"Do you need any other languages? For example German, French, Spanish, Polish, Italian, Portuguese, Russian… Just tell me and I'll check what's available.\"\n\nIf the user names a language, look up the available models at https://github.com/rhasspy/piper/blob/master/VOICES.md and list the options. Download whatever the user picks using the same downloadVoices() call.\n\n3c. Download everything at once:\n\nconst result = await downloadVoices(['en_US-ryan-medium', 'en_US-amy-medium', /* + any others */]);\n// result.downloaded — succeeded\n// result.failed     — [{stem, error}] if any failed\n\nEach voice requires internet access. Download takes ~1–2 min per voice on a typical connection.\n\nIf any downloads fail:\n\nCheck internet connectivity\nVerify the stem exists at https://github.com/rhasspy/piper/blob/master/VOICES.md\nOffer to retry"
      },
      {
        "title": "Step 4 — play samples so the user can choose",
        "body": "After downloading, generate a short audio sample for each downloaded voice and send it to the user.\n\nFor each voice, use a greeting in the voice's language:\n\nEnglish: \"Hello, I'm [name]. How can I help you today?\"\nGerman: \"Hallo, ich heiße [Name]. Wie kann ich Ihnen helfen?\"\nFrench: \"Bonjour, je m'appelle [prénom]. Comment puis-je vous aider?\"\nSpanish: \"Hola, me llamo [nombre]. ¿Cómo puedo ayudarte?\"\nPolish: \"Cześć, mam na imię [imię]. Jak mogę Ci pomóc?\"\nItalian: \"Ciao, mi chiamo [nome]. Come posso aiutarti?\"\nPortuguese: \"Olá, meu nome é [nome]. Como posso ajudar?\"\nRussian: \"Привет, меня зовут [имя]. Чем могу помочь?\"\nFor other languages: use an equivalent native greeting.\n\nReplace [name] with the voice name (e.g. Ryan, Amy, Thorsten).\n\nconst sample = await tts({ text: 'Hello, I\\'m Ryan. How can I help you today?', voice: 'en_US-ryan-medium' });\n// send sample.path to the user as a voice message\n\nSend all samples, then ask: \"Which voice do you prefer? Or shall I download a different one?\""
      },
      {
        "title": "Step 5 — choose speech speed",
        "body": "After the user picks a voice, ask:\n\"How fast should I speak? Normal is 100%. Some options: 125% (faster), 115% (slightly faster), 100% (normal), 80% (slower) — or tell me a percentage.\"\n\nAlways present speed as a percentage to the user. Never mention lengthScale directly.\n\nlengthScale is the internal duration multiplier — lower = faster. To convert: lengthScale = 1 / (speed% / 100).\nExamples:\n\n125% speed → lengthScale 0.8\n115% speed → lengthScale 0.87\n100% speed → lengthScale 1.0 (default)\n80% speed  → lengthScale 1.25\n\nGenerate a short sample at the chosen speed so the user can hear the difference:\n\nconst sample = await tts({ text: 'This is how I sound at this speed.', voice: 'chosen-voice', lengthScale: 0.8 });\n// send sample.path to the user\n\nConfirm with the user, then offer to save it permanently:\n\"Should I save this as your default speed? It'll be used automatically every session.\"\n\nIf the user agrees:\n\nawait saveConfig({ lengthScale: 0.8 });\n\nOnce saved, tts() reads it from config.json in the skill directory automatically — no need to pass lengthScale on every call."
      },
      {
        "title": "Step 6 — note the preferred voice and speed",
        "body": "Once confirmed, remember both voice and lengthScale for the session. Pass them to every subsequent tts() call unless the user asks to change them."
      },
      {
        "title": "Before first use — always call status()",
        "body": "Always call status() before the first tts() call in a session to determine what is needed.\n\nstageMeaningWhat to doreadyFully installed, at least one voice model presentProceed with tts()not-setupPiper not installedAsk user for confirmation, then call setup()no-piperVenv exists but piper binary missingAsk user for confirmation, then call setup()no-modelPiper installed but no voice model downloadedFollow Steps 3–5 of first-run flow above\n\nIMPORTANT: Always ask the user for confirmation before calling setup().\nIt installs the piper-tts package from PyPI into a venv inside the skill directory."
      },
      {
        "title": "Usage",
        "body": "Input: text, optional format (\"ogg\" or \"wav\"), optional voice (model stem), optional lengthScale (speech speed, default 1.0)\nOutput: path to generated file (usually .ogg)"
      },
      {
        "title": "Controlling voice and language",
        "body": "To list installed voices, call listVoices() — returns stems of all installed .onnx models.\nNever assume a fixed list; it varies per user and installation.\n\nAuto-detection (no voice param):\nThe script detects language from the text using character and script analysis:\n\nNon-Latin scripts: Cyrillic (Russian, Ukrainian, Bulgarian), Greek, Arabic, Persian, Chinese, Japanese, Korean, Georgian\nLatin-script languages: Vietnamese, Polish, Romanian, Turkish, Czech, Slovak, Hungarian, Portuguese, Spanish, Catalan, German, Finnish, Scandinavian (Swedish, Norwegian, Danish), French, Italian\nFallback: English keywords → first English model → any installed model\n\nAuto-detection is best-effort. For reliable results with a specific language, always pass the voice parameter explicitly.\n\nExplicit override: set PIPER_VOICE_MODEL env var to a full .onnx path (overrides everything).\n\nWhen the user requests a specific voice or language:\n\nCall listVoices() to see what is installed\nPass the matching stem as voice to tts(), e.g. voice: \"en_US-amy-medium\"\nIf the requested voice is not installed, offer to download it with downloadVoices([stem])\n\nTo switch back to auto-detect, omit the voice parameter."
      },
      {
        "title": "Downloading additional voices",
        "body": "The user may say things like \"I don't like this voice, use a female one\" or\n\"Download a German voice\". When this happens:\n\nFind the model at https://github.com/rhasspy/piper/blob/master/VOICES.md\nConfirm the stem (e.g. de_DE-thorsten-medium) and call downloadVoices([stem])\nGenerate a sample and send it to the user\nConfirm with listVoices() — the new voice is immediately usable"
      },
      {
        "title": "Removing voices",
        "body": "The user may say \"remove that voice\" or \"I don't need the German voice anymore\". When this happens:\n\nCall listVoices() to confirm which voices are installed\nConfirm with the user which voice to remove\nCall removeVoice(stem) — e.g. removeVoice('de_DE-thorsten-medium')\nReturns { removed, filesDeleted } on success\nIf the removed voice was the user's preferred voice, ask them to pick a new one\n\nNever remove the last remaining voice without warning the user that TTS will stop working."
      },
      {
        "title": "Changing speech speed",
        "body": "The user may say things like \"speak faster\", \"too slow\", or \"speed it up\". When this happens:\n\nAsk what speed they want in %, or suggest: 125% (faster), 115%, 100% (normal), 80% (slower)\nConvert their % to lengthScale: lengthScale = 1 / (speed% / 100)\nGenerate a short sample: await tts({ text: '...', voice: 'current-voice', lengthScale: 0.8 })\nSend the sample and confirm\nOffer to persist: \"Save this as default?\" — if yes, call saveConfig({ lengthScale: 0.8 })\nUse the new lengthScale for all subsequent tts() calls in the session"
      },
      {
        "title": "Where files are written",
        "body": "OPENCLAW_WORKSPACE/tts/ if OPENCLAW_WORKSPACE env var is set\notherwise: ~/.openclaw/workspace/tts/"
      },
      {
        "title": "Dependencies",
        "body": "python3 (3.8+) — required for setup() to create the venv\nffmpeg — for WAV → OGG/Opus conversion\nespeak-ng — system library used by Piper internally; setup() checks for it and warns if missing.\nInstall: sudo apt install espeak-ng (Debian/Ubuntu), sudo dnf install espeak-ng (Fedora),\nbrew install espeak (macOS)\nAt least one Piper .onnx + .onnx.json voice model pair in the skill directory"
      },
      {
        "title": "Platform support",
        "body": "Linux x86_64: fully supported\nmacOS x86_64 / arm64: fully supported\nLinux ARM: may require building piper-tts from source\nWindows: not supported"
      },
      {
        "title": "Remove",
        "body": "rm -rf ~/.openclaw/skills/local-piper-tts-multilang-secure\n\nThis removes everything: skill code, venv, and all voice models."
      }
    ],
    "body": "local-piper-tts-multilang-secure\nDescription\n\nLocal (offline) text-to-speech via Piper.\n\nPurpose: generate audio files (OGG/Opus by default) from text, fully offline. No sending is performed by the skill — sending is handled by the agent after the file is ready.\n\nFeatures\nFully offline (no API keys)\nSelf-contained setup via setup() — installs Piper into an isolated venv, no system-wide changes\nAutomatic language detection for 20+ languages with English as default\nPer-call voice selection via voice parameter\nOn-demand voice download via downloadVoices() — no models bundled, choose what you need\nVoice removal via removeVoice() — clean up voices you no longer want\nExtensible: add any language by installing a Piper .onnx model\nWrites outputs into OpenClaw workspace\nFirst-run flow — full agent procedure\n\nFollow this sequence exactly when the user asks to use TTS for the first time in a setup context.\n\nStep 1 — check status\nconst s = await status();\n\nStep 2 — install Piper if needed\n\nIf s.stage is not-setup or no-piper:\n\nTell the user: \"To use local TTS I need to install piper-tts into the skill's venv (~30 seconds, one-time). OK to proceed?\"\nWait for confirmation, then call setup().\nIf setup returns a step containing \"WARNING: espeak-ng not found\", relay the warning and install instructions to the user.\nCall status() again after setup completes.\nStep 3 — offer voice download if no models present\n\nIf s.stage is no-model (Piper installed but no .onnx files):\n\n3a. Offer English defaults: Explain that two English voices are available as defaults (~65 MB each):\n\nen_US-ryan-medium — male, American\nen_US-amy-medium — female, American\n\nAsk which they want, or both: \"Which English voice(s) should I download? Ryan (male), Amy (female), or both?\"\n\n3b. Ask about other languages: After the English choice, ask: \"Do you need any other languages? For example German, French, Spanish, Polish, Italian, Portuguese, Russian… Just tell me and I'll check what's available.\"\n\nIf the user names a language, look up the available models at https://github.com/rhasspy/piper/blob/master/VOICES.md and list the options. Download whatever the user picks using the same downloadVoices() call.\n\n3c. Download everything at once:\n\nconst result = await downloadVoices(['en_US-ryan-medium', 'en_US-amy-medium', /* + any others */]);\n// result.downloaded — succeeded\n// result.failed     — [{stem, error}] if any failed\n\n\nEach voice requires internet access. Download takes ~1–2 min per voice on a typical connection.\n\nIf any downloads fail:\n\nCheck internet connectivity\nVerify the stem exists at https://github.com/rhasspy/piper/blob/master/VOICES.md\nOffer to retry\nStep 4 — play samples so the user can choose\n\nAfter downloading, generate a short audio sample for each downloaded voice and send it to the user.\n\nFor each voice, use a greeting in the voice's language:\n\nEnglish: \"Hello, I'm [name]. How can I help you today?\"\nGerman: \"Hallo, ich heiße [Name]. Wie kann ich Ihnen helfen?\"\nFrench: \"Bonjour, je m'appelle [prénom]. Comment puis-je vous aider?\"\nSpanish: \"Hola, me llamo [nombre]. ¿Cómo puedo ayudarte?\"\nPolish: \"Cześć, mam na imię [imię]. Jak mogę Ci pomóc?\"\nItalian: \"Ciao, mi chiamo [nome]. Come posso aiutarti?\"\nPortuguese: \"Olá, meu nome é [nome]. Como posso ajudar?\"\nRussian: \"Привет, меня зовут [имя]. Чем могу помочь?\"\nFor other languages: use an equivalent native greeting.\n\nReplace [name] with the voice name (e.g. Ryan, Amy, Thorsten).\n\nconst sample = await tts({ text: 'Hello, I\\'m Ryan. How can I help you today?', voice: 'en_US-ryan-medium' });\n// send sample.path to the user as a voice message\n\n\nSend all samples, then ask: \"Which voice do you prefer? Or shall I download a different one?\"\n\nStep 5 — choose speech speed\n\nAfter the user picks a voice, ask: \"How fast should I speak? Normal is 100%. Some options: 125% (faster), 115% (slightly faster), 100% (normal), 80% (slower) — or tell me a percentage.\"\n\nAlways present speed as a percentage to the user. Never mention lengthScale directly.\n\nlengthScale is the internal duration multiplier — lower = faster. To convert: lengthScale = 1 / (speed% / 100). Examples:\n\n125% speed → lengthScale 0.8\n115% speed → lengthScale 0.87\n100% speed → lengthScale 1.0 (default)\n80% speed → lengthScale 1.25\n\nGenerate a short sample at the chosen speed so the user can hear the difference:\n\nconst sample = await tts({ text: 'This is how I sound at this speed.', voice: 'chosen-voice', lengthScale: 0.8 });\n// send sample.path to the user\n\n\nConfirm with the user, then offer to save it permanently: \"Should I save this as your default speed? It'll be used automatically every session.\"\n\nIf the user agrees:\n\nawait saveConfig({ lengthScale: 0.8 });\n\n\nOnce saved, tts() reads it from config.json in the skill directory automatically — no need to pass lengthScale on every call.\n\nStep 6 — note the preferred voice and speed\n\nOnce confirmed, remember both voice and lengthScale for the session. Pass them to every subsequent tts() call unless the user asks to change them.\n\nBefore first use — always call status()\n\nAlways call status() before the first tts() call in a session to determine what is needed.\n\nstage\tMeaning\tWhat to do\nready\tFully installed, at least one voice model present\tProceed with tts()\nnot-setup\tPiper not installed\tAsk user for confirmation, then call setup()\nno-piper\tVenv exists but piper binary missing\tAsk user for confirmation, then call setup()\nno-model\tPiper installed but no voice model downloaded\tFollow Steps 3–5 of first-run flow above\n\nIMPORTANT: Always ask the user for confirmation before calling setup(). It installs the piper-tts package from PyPI into a venv inside the skill directory.\n\nUsage\nInput: text, optional format (\"ogg\" or \"wav\"), optional voice (model stem), optional lengthScale (speech speed, default 1.0)\nOutput: path to generated file (usually .ogg)\nControlling voice and language\n\nTo list installed voices, call listVoices() — returns stems of all installed .onnx models. Never assume a fixed list; it varies per user and installation.\n\nAuto-detection (no voice param): The script detects language from the text using character and script analysis:\n\nNon-Latin scripts: Cyrillic (Russian, Ukrainian, Bulgarian), Greek, Arabic, Persian, Chinese, Japanese, Korean, Georgian\nLatin-script languages: Vietnamese, Polish, Romanian, Turkish, Czech, Slovak, Hungarian, Portuguese, Spanish, Catalan, German, Finnish, Scandinavian (Swedish, Norwegian, Danish), French, Italian\nFallback: English keywords → first English model → any installed model\n\nAuto-detection is best-effort. For reliable results with a specific language, always pass the voice parameter explicitly.\n\nExplicit override: set PIPER_VOICE_MODEL env var to a full .onnx path (overrides everything).\n\nWhen the user requests a specific voice or language:\n\nCall listVoices() to see what is installed\nPass the matching stem as voice to tts(), e.g. voice: \"en_US-amy-medium\"\nIf the requested voice is not installed, offer to download it with downloadVoices([stem])\n\nTo switch back to auto-detect, omit the voice parameter.\n\nDownloading additional voices\n\nThe user may say things like \"I don't like this voice, use a female one\" or \"Download a German voice\". When this happens:\n\nFind the model at https://github.com/rhasspy/piper/blob/master/VOICES.md\nConfirm the stem (e.g. de_DE-thorsten-medium) and call downloadVoices([stem])\nGenerate a sample and send it to the user\nConfirm with listVoices() — the new voice is immediately usable\nRemoving voices\n\nThe user may say \"remove that voice\" or \"I don't need the German voice anymore\". When this happens:\n\nCall listVoices() to confirm which voices are installed\nConfirm with the user which voice to remove\nCall removeVoice(stem) — e.g. removeVoice('de_DE-thorsten-medium')\nReturns { removed, filesDeleted } on success\nIf the removed voice was the user's preferred voice, ask them to pick a new one\n\nNever remove the last remaining voice without warning the user that TTS will stop working.\n\nChanging speech speed\n\nThe user may say things like \"speak faster\", \"too slow\", or \"speed it up\". When this happens:\n\nAsk what speed they want in %, or suggest: 125% (faster), 115%, 100% (normal), 80% (slower)\nConvert their % to lengthScale: lengthScale = 1 / (speed% / 100)\nGenerate a short sample: await tts({ text: '...', voice: 'current-voice', lengthScale: 0.8 })\nSend the sample and confirm\nOffer to persist: \"Save this as default?\" — if yes, call saveConfig({ lengthScale: 0.8 })\nUse the new lengthScale for all subsequent tts() calls in the session\nWhere files are written\nOPENCLAW_WORKSPACE/tts/ if OPENCLAW_WORKSPACE env var is set\notherwise: ~/.openclaw/workspace/tts/\nDependencies\npython3 (3.8+) — required for setup() to create the venv\nffmpeg — for WAV → OGG/Opus conversion\nespeak-ng — system library used by Piper internally; setup() checks for it and warns if missing. Install: sudo apt install espeak-ng (Debian/Ubuntu), sudo dnf install espeak-ng (Fedora), brew install espeak (macOS)\nAt least one Piper .onnx + .onnx.json voice model pair in the skill directory\nPlatform support\nLinux x86_64: fully supported\nmacOS x86_64 / arm64: fully supported\nLinux ARM: may require building piper-tts from source\nWindows: not supported\nRemove\nrm -rf ~/.openclaw/skills/local-piper-tts-multilang-secure\n\n\nThis removes everything: skill code, venv, and all voice models."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/szafranski/local-piper-tts-multilang-secure",
    "publisherUrl": "https://clawhub.ai/szafranski/local-piper-tts-multilang-secure",
    "owner": "szafranski",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/local-piper-tts-multilang-secure",
    "downloadUrl": "https://openagent3.xyz/downloads/local-piper-tts-multilang-secure",
    "agentUrl": "https://openagent3.xyz/skills/local-piper-tts-multilang-secure/agent",
    "manifestUrl": "https://openagent3.xyz/skills/local-piper-tts-multilang-secure/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/local-piper-tts-multilang-secure/agent.md"
  }
}