{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ai-voice-cloning",
    "name": "Ai Voice Cloning",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/okaris/ai-voice-cloning",
    "canonicalUrl": "https://clawhub.ai/okaris/ai-voice-cloning",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ai-voice-cloning",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-voice-cloning",
    "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": "2026-04-23T16:43:11.935Z",
      "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/ai-voice-cloning"
    },
    "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/ai-voice-cloning",
    "agentPageUrl": "https://openagent3.xyz/skills/ai-voice-cloning/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-voice-cloning/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-voice-cloning/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": "AI Voice Generation",
        "body": "Generate natural AI voices via inference.sh CLI."
      },
      {
        "title": "Quick Start",
        "body": "curl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Generate speech\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Hello! This is an AI-generated voice that sounds natural and engaging.\",\n  \"voice\": \"af_sarah\"\n}'\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available."
      },
      {
        "title": "Available Models",
        "body": "ModelApp IDBest ForKokoro TTSinfsh/kokoro-ttsNatural, multiple voicesDIAinfsh/dia-ttsConversational, expressiveChatterboxinfsh/chatterboxCasual, entertainmentHiggsinfsh/higgs-ttsProfessional narrationVibeVoiceinfsh/vibevoiceEmotional range"
      },
      {
        "title": "American English",
        "body": "Voice IDGenderStyleaf_sarahFemaleWarm, friendlyaf_nicoleFemaleProfessionalaf_skyFemaleYouthfulam_michaelMaleAuthoritativeam_adamMaleConversationalam_echoMaleClear, neutral"
      },
      {
        "title": "British English",
        "body": "Voice IDGenderStylebf_emmaFemaleRefinedbf_isabellaFemaleWarmbm_georgeMaleClassicbm_lewisMaleModern"
      },
      {
        "title": "Professional Narration",
        "body": "infsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Welcome to our quarterly earnings call. Today we will discuss the financial performance and strategic initiatives for the past quarter.\",\n  \"voice\": \"am_michael\",\n  \"speed\": 1.0\n}'"
      },
      {
        "title": "Conversational Style",
        "body": "infsh app run infsh/dia-tts --input '{\n  \"text\": \"Hey, so I was thinking about that project we discussed. What if we tried a different approach?\",\n  \"voice\": \"conversational\"\n}'"
      },
      {
        "title": "Audiobook Narration",
        "body": "infsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Chapter One. The morning mist hung low over the valley as Sarah made her way down the winding path. She had been walking for hours.\",\n  \"voice\": \"bf_emma\",\n  \"speed\": 0.9\n}'"
      },
      {
        "title": "Video Voiceover",
        "body": "infsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Introducing the next generation of productivity. Work smarter, not harder.\",\n  \"voice\": \"af_nicole\",\n  \"speed\": 1.1\n}'"
      },
      {
        "title": "Podcast Host",
        "body": "infsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Welcome back to Tech Talk! Im your host, and today we are diving deep into the world of artificial intelligence.\",\n  \"voice\": \"am_adam\"\n}'"
      },
      {
        "title": "Multi-Voice Conversation",
        "body": "# Generate dialogue between two speakers\n# Speaker 1\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Have you seen the latest AI developments? Its incredible how fast things are moving.\",\n  \"voice\": \"am_michael\"\n}' > speaker1.json\n\n# Speaker 2\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"I know, right? Just last week I tried that new image generator and was blown away.\",\n  \"voice\": \"af_sarah\"\n}' > speaker2.json\n\n# Merge conversation\ninfsh app run infsh/media-merger --input '{\n  \"audio_files\": [\"<speaker1-url>\", \"<speaker2-url>\"],\n  \"crossfade_ms\": 300\n}'"
      },
      {
        "title": "Chunked Processing",
        "body": "For content over 5000 characters, split into chunks:\n\n# Process long text in chunks\nTEXT=\"Your very long text here...\"\n\n# Split and generate\n# Chunk 1\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"<chunk-1>\",\n  \"voice\": \"bf_emma\"\n}' > chunk1.json\n\n# Chunk 2\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"<chunk-2>\",\n  \"voice\": \"bf_emma\"\n}' > chunk2.json\n\n# Merge chunks\ninfsh app run infsh/media-merger --input '{\n  \"audio_files\": [\"<chunk1-url>\", \"<chunk2-url>\"],\n  \"crossfade_ms\": 100\n}'"
      },
      {
        "title": "Add Voiceover to Video",
        "body": "# 1. Generate voiceover\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"This stunning footage shows the beauty of nature in its purest form.\",\n  \"voice\": \"am_michael\"\n}' > voiceover.json\n\n# 2. Merge with video\ninfsh app run infsh/media-merger --input '{\n  \"video_url\": \"https://your-video.mp4\",\n  \"audio_url\": \"<voiceover-url>\"\n}'"
      },
      {
        "title": "Create Talking Head",
        "body": "# 1. Generate speech\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Hi, Im excited to share some updates with you today.\",\n  \"voice\": \"af_sarah\"\n}' > speech.json\n\n# 2. Animate with avatar\ninfsh app run bytedance/omnihuman-1-5 --input '{\n  \"image_url\": \"https://portrait.jpg\",\n  \"audio_url\": \"<speech-url>\"\n}'"
      },
      {
        "title": "Speed and Pacing",
        "body": "SpeedEffectUse For0.8Slow, deliberateAudiobooks, meditation0.9Slightly slowEducation, tutorials1.0NormalGeneral purpose1.1Slightly fastCommercials, energy1.2FastQuick announcements\n\n# Slow narration\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Take a deep breath. Let yourself relax.\",\n  \"voice\": \"bf_emma\",\n  \"speed\": 0.8\n}'"
      },
      {
        "title": "Punctuation for Pacing",
        "body": "Use punctuation to control speech rhythm:\n\nPunctuationEffectPeriod .Full pauseComma ,Brief pause...Extended pause!Emphasis?Question intonation-Quick break\n\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Wait... Did you hear that? Something is coming. Something big!\",\n  \"voice\": \"am_adam\"\n}'"
      },
      {
        "title": "Best Practices",
        "body": "Match voice to content - Professional voice for business, casual for social\nUse punctuation - Control pacing with periods and commas\nKeep sentences short - Easier to generate and sounds more natural\nTest different voices - Same text sounds different across voices\nAdjust speed - Slightly slower often sounds more natural\nBreak long content - Process in chunks for consistency"
      },
      {
        "title": "Use Cases",
        "body": "Voiceovers - Video narration, commercials\nAudiobooks - Full book narration\nPodcasts - AI hosts and guests\nE-learning - Course narration\nAccessibility - Screen reader content\nIVR - Phone system messages\nContent localization - Translate and voice"
      },
      {
        "title": "Related Skills",
        "body": "# All TTS models\nnpx skills add inference-sh/skills@text-to-speech\n\n# Podcast creation\nnpx skills add inference-sh/skills@ai-podcast-creation\n\n# AI avatars\nnpx skills add inference-sh/skills@ai-avatar-video\n\n# Video generation\nnpx skills add inference-sh/skills@ai-video-generation\n\n# Full platform skill\nnpx skills add inference-sh/skills@inference-sh\n\nBrowse audio apps: infsh app list --category audio"
      }
    ],
    "body": "AI Voice Generation\n\nGenerate natural AI voices via inference.sh CLI.\n\nQuick Start\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Generate speech\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Hello! This is an AI-generated voice that sounds natural and engaging.\",\n  \"voice\": \"af_sarah\"\n}'\n\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.\n\nAvailable Models\nModel\tApp ID\tBest For\nKokoro TTS\tinfsh/kokoro-tts\tNatural, multiple voices\nDIA\tinfsh/dia-tts\tConversational, expressive\nChatterbox\tinfsh/chatterbox\tCasual, entertainment\nHiggs\tinfsh/higgs-tts\tProfessional narration\nVibeVoice\tinfsh/vibevoice\tEmotional range\nKokoro Voice Library\nAmerican English\nVoice ID\tGender\tStyle\naf_sarah\tFemale\tWarm, friendly\naf_nicole\tFemale\tProfessional\naf_sky\tFemale\tYouthful\nam_michael\tMale\tAuthoritative\nam_adam\tMale\tConversational\nam_echo\tMale\tClear, neutral\nBritish English\nVoice ID\tGender\tStyle\nbf_emma\tFemale\tRefined\nbf_isabella\tFemale\tWarm\nbm_george\tMale\tClassic\nbm_lewis\tMale\tModern\nVoice Generation Examples\nProfessional Narration\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Welcome to our quarterly earnings call. Today we will discuss the financial performance and strategic initiatives for the past quarter.\",\n  \"voice\": \"am_michael\",\n  \"speed\": 1.0\n}'\n\nConversational Style\ninfsh app run infsh/dia-tts --input '{\n  \"text\": \"Hey, so I was thinking about that project we discussed. What if we tried a different approach?\",\n  \"voice\": \"conversational\"\n}'\n\nAudiobook Narration\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Chapter One. The morning mist hung low over the valley as Sarah made her way down the winding path. She had been walking for hours.\",\n  \"voice\": \"bf_emma\",\n  \"speed\": 0.9\n}'\n\nVideo Voiceover\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Introducing the next generation of productivity. Work smarter, not harder.\",\n  \"voice\": \"af_nicole\",\n  \"speed\": 1.1\n}'\n\nPodcast Host\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Welcome back to Tech Talk! Im your host, and today we are diving deep into the world of artificial intelligence.\",\n  \"voice\": \"am_adam\"\n}'\n\nMulti-Voice Conversation\n# Generate dialogue between two speakers\n# Speaker 1\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Have you seen the latest AI developments? Its incredible how fast things are moving.\",\n  \"voice\": \"am_michael\"\n}' > speaker1.json\n\n# Speaker 2\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"I know, right? Just last week I tried that new image generator and was blown away.\",\n  \"voice\": \"af_sarah\"\n}' > speaker2.json\n\n# Merge conversation\ninfsh app run infsh/media-merger --input '{\n  \"audio_files\": [\"<speaker1-url>\", \"<speaker2-url>\"],\n  \"crossfade_ms\": 300\n}'\n\nLong-Form Content\nChunked Processing\n\nFor content over 5000 characters, split into chunks:\n\n# Process long text in chunks\nTEXT=\"Your very long text here...\"\n\n# Split and generate\n# Chunk 1\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"<chunk-1>\",\n  \"voice\": \"bf_emma\"\n}' > chunk1.json\n\n# Chunk 2\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"<chunk-2>\",\n  \"voice\": \"bf_emma\"\n}' > chunk2.json\n\n# Merge chunks\ninfsh app run infsh/media-merger --input '{\n  \"audio_files\": [\"<chunk1-url>\", \"<chunk2-url>\"],\n  \"crossfade_ms\": 100\n}'\n\nVoice + Video Workflow\nAdd Voiceover to Video\n# 1. Generate voiceover\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"This stunning footage shows the beauty of nature in its purest form.\",\n  \"voice\": \"am_michael\"\n}' > voiceover.json\n\n# 2. Merge with video\ninfsh app run infsh/media-merger --input '{\n  \"video_url\": \"https://your-video.mp4\",\n  \"audio_url\": \"<voiceover-url>\"\n}'\n\nCreate Talking Head\n# 1. Generate speech\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Hi, Im excited to share some updates with you today.\",\n  \"voice\": \"af_sarah\"\n}' > speech.json\n\n# 2. Animate with avatar\ninfsh app run bytedance/omnihuman-1-5 --input '{\n  \"image_url\": \"https://portrait.jpg\",\n  \"audio_url\": \"<speech-url>\"\n}'\n\nSpeed and Pacing\nSpeed\tEffect\tUse For\n0.8\tSlow, deliberate\tAudiobooks, meditation\n0.9\tSlightly slow\tEducation, tutorials\n1.0\tNormal\tGeneral purpose\n1.1\tSlightly fast\tCommercials, energy\n1.2\tFast\tQuick announcements\n# Slow narration\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Take a deep breath. Let yourself relax.\",\n  \"voice\": \"bf_emma\",\n  \"speed\": 0.8\n}'\n\nPunctuation for Pacing\n\nUse punctuation to control speech rhythm:\n\nPunctuation\tEffect\nPeriod .\tFull pause\nComma ,\tBrief pause\n...\tExtended pause\n!\tEmphasis\n?\tQuestion intonation\n-\tQuick break\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Wait... Did you hear that? Something is coming. Something big!\",\n  \"voice\": \"am_adam\"\n}'\n\nBest Practices\nMatch voice to content - Professional voice for business, casual for social\nUse punctuation - Control pacing with periods and commas\nKeep sentences short - Easier to generate and sounds more natural\nTest different voices - Same text sounds different across voices\nAdjust speed - Slightly slower often sounds more natural\nBreak long content - Process in chunks for consistency\nUse Cases\nVoiceovers - Video narration, commercials\nAudiobooks - Full book narration\nPodcasts - AI hosts and guests\nE-learning - Course narration\nAccessibility - Screen reader content\nIVR - Phone system messages\nContent localization - Translate and voice\nRelated Skills\n# All TTS models\nnpx skills add inference-sh/skills@text-to-speech\n\n# Podcast creation\nnpx skills add inference-sh/skills@ai-podcast-creation\n\n# AI avatars\nnpx skills add inference-sh/skills@ai-avatar-video\n\n# Video generation\nnpx skills add inference-sh/skills@ai-video-generation\n\n# Full platform skill\nnpx skills add inference-sh/skills@inference-sh\n\n\nBrowse audio apps: infsh app list --category audio"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/okaris/ai-voice-cloning",
    "publisherUrl": "https://clawhub.ai/okaris/ai-voice-cloning",
    "owner": "okaris",
    "version": "0.1.5",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ai-voice-cloning",
    "downloadUrl": "https://openagent3.xyz/downloads/ai-voice-cloning",
    "agentUrl": "https://openagent3.xyz/skills/ai-voice-cloning/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-voice-cloning/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-voice-cloning/agent.md"
  }
}