{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ai-avatar-video",
    "name": "Ai Avatar Video",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/okaris/ai-avatar-video",
    "canonicalUrl": "https://clawhub.ai/okaris/ai-avatar-video",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ai-avatar-video",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-avatar-video",
    "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-avatar-video"
    },
    "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-avatar-video",
    "agentPageUrl": "https://openagent3.xyz/skills/ai-avatar-video/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-avatar-video/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-avatar-video/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 Avatar & Talking Head Videos",
        "body": "Create AI avatars and talking head videos via inference.sh CLI."
      },
      {
        "title": "Quick Start",
        "body": "curl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Create avatar video from image + audio\ninfsh app run bytedance/omnihuman-1-5 --input '{\n  \"image_url\": \"https://portrait.jpg\",\n  \"audio_url\": \"https://speech.mp3\"\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 ForOmniHuman 1.5bytedance/omnihuman-1-5Multi-character, best qualityOmniHuman 1.0bytedance/omnihuman-1-0Single characterFabric 1.0falai/fabric-1-0Image talks with lipsyncPixVerse Lipsyncfalai/pixverse-lipsyncHighly realistic"
      },
      {
        "title": "Search Avatar Apps",
        "body": "infsh app list --search \"omnihuman\"\ninfsh app list --search \"lipsync\"\ninfsh app list --search \"fabric\""
      },
      {
        "title": "OmniHuman 1.5 (Multi-Character)",
        "body": "infsh app run bytedance/omnihuman-1-5 --input '{\n  \"image_url\": \"https://portrait.jpg\",\n  \"audio_url\": \"https://speech.mp3\"\n}'\n\nSupports specifying which character to drive in multi-person images."
      },
      {
        "title": "Fabric 1.0 (Image Talks)",
        "body": "infsh app run falai/fabric-1-0 --input '{\n  \"image_url\": \"https://face.jpg\",\n  \"audio_url\": \"https://audio.mp3\"\n}'"
      },
      {
        "title": "PixVerse Lipsync",
        "body": "infsh app run falai/pixverse-lipsync --input '{\n  \"image_url\": \"https://portrait.jpg\",\n  \"audio_url\": \"https://speech.mp3\"\n}'\n\nGenerates highly realistic lipsync from any audio."
      },
      {
        "title": "Full Workflow: TTS + Avatar",
        "body": "# 1. Generate speech from text\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Welcome to our product demo. Today I will show you...\"\n}' > speech.json\n\n# 2. Create avatar video with the speech\ninfsh app run bytedance/omnihuman-1-5 --input '{\n  \"image_url\": \"https://presenter-photo.jpg\",\n  \"audio_url\": \"<audio-url-from-step-1>\"\n}'"
      },
      {
        "title": "Full Workflow: Dub Video in Another Language",
        "body": "# 1. Transcribe original video\ninfsh app run infsh/fast-whisper-large-v3 --input '{\"audio_url\": \"https://video.mp4\"}' > transcript.json\n\n# 2. Translate text (manually or with an LLM)\n\n# 3. Generate speech in new language\ninfsh app run infsh/kokoro-tts --input '{\"text\": \"<translated-text>\"}' > new_speech.json\n\n# 4. Lipsync the original video with new audio\ninfsh app run infsh/latentsync-1-6 --input '{\n  \"video_url\": \"https://original-video.mp4\",\n  \"audio_url\": \"<new-audio-url>\"\n}'"
      },
      {
        "title": "Use Cases",
        "body": "Marketing: Product demos with AI presenter\nEducation: Course videos, explainers\nLocalization: Dub content in multiple languages\nSocial Media: Consistent virtual influencer\nCorporate: Training videos, announcements"
      },
      {
        "title": "Tips",
        "body": "Use high-quality portrait photos (front-facing, good lighting)\nAudio should be clear with minimal background noise\nOmniHuman 1.5 supports multiple people in one image\nLatentSync is best for syncing existing videos to new audio"
      },
      {
        "title": "Related Skills",
        "body": "# Full platform skill (all 150+ apps)\nnpx skills add inference-sh/skills@inference-sh\n\n# Text-to-speech (generate audio for avatars)\nnpx skills add inference-sh/skills@text-to-speech\n\n# Speech-to-text (transcribe for dubbing)\nnpx skills add inference-sh/skills@speech-to-text\n\n# Video generation\nnpx skills add inference-sh/skills@ai-video-generation\n\n# Image generation (create avatar images)\nnpx skills add inference-sh/skills@ai-image-generation\n\nBrowse all video apps: infsh app list --category video"
      },
      {
        "title": "Documentation",
        "body": "Running Apps - How to run apps via CLI\nContent Pipeline Example - Building media workflows\nStreaming Results - Real-time progress updates"
      }
    ],
    "body": "AI Avatar & Talking Head Videos\n\nCreate AI avatars and talking head videos via inference.sh CLI.\n\nQuick Start\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Create avatar video from image + audio\ninfsh app run bytedance/omnihuman-1-5 --input '{\n  \"image_url\": \"https://portrait.jpg\",\n  \"audio_url\": \"https://speech.mp3\"\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\nOmniHuman 1.5\tbytedance/omnihuman-1-5\tMulti-character, best quality\nOmniHuman 1.0\tbytedance/omnihuman-1-0\tSingle character\nFabric 1.0\tfalai/fabric-1-0\tImage talks with lipsync\nPixVerse Lipsync\tfalai/pixverse-lipsync\tHighly realistic\nSearch Avatar Apps\ninfsh app list --search \"omnihuman\"\ninfsh app list --search \"lipsync\"\ninfsh app list --search \"fabric\"\n\nExamples\nOmniHuman 1.5 (Multi-Character)\ninfsh app run bytedance/omnihuman-1-5 --input '{\n  \"image_url\": \"https://portrait.jpg\",\n  \"audio_url\": \"https://speech.mp3\"\n}'\n\n\nSupports specifying which character to drive in multi-person images.\n\nFabric 1.0 (Image Talks)\ninfsh app run falai/fabric-1-0 --input '{\n  \"image_url\": \"https://face.jpg\",\n  \"audio_url\": \"https://audio.mp3\"\n}'\n\nPixVerse Lipsync\ninfsh app run falai/pixverse-lipsync --input '{\n  \"image_url\": \"https://portrait.jpg\",\n  \"audio_url\": \"https://speech.mp3\"\n}'\n\n\nGenerates highly realistic lipsync from any audio.\n\nFull Workflow: TTS + Avatar\n# 1. Generate speech from text\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Welcome to our product demo. Today I will show you...\"\n}' > speech.json\n\n# 2. Create avatar video with the speech\ninfsh app run bytedance/omnihuman-1-5 --input '{\n  \"image_url\": \"https://presenter-photo.jpg\",\n  \"audio_url\": \"<audio-url-from-step-1>\"\n}'\n\nFull Workflow: Dub Video in Another Language\n# 1. Transcribe original video\ninfsh app run infsh/fast-whisper-large-v3 --input '{\"audio_url\": \"https://video.mp4\"}' > transcript.json\n\n# 2. Translate text (manually or with an LLM)\n\n# 3. Generate speech in new language\ninfsh app run infsh/kokoro-tts --input '{\"text\": \"<translated-text>\"}' > new_speech.json\n\n# 4. Lipsync the original video with new audio\ninfsh app run infsh/latentsync-1-6 --input '{\n  \"video_url\": \"https://original-video.mp4\",\n  \"audio_url\": \"<new-audio-url>\"\n}'\n\nUse Cases\nMarketing: Product demos with AI presenter\nEducation: Course videos, explainers\nLocalization: Dub content in multiple languages\nSocial Media: Consistent virtual influencer\nCorporate: Training videos, announcements\nTips\nUse high-quality portrait photos (front-facing, good lighting)\nAudio should be clear with minimal background noise\nOmniHuman 1.5 supports multiple people in one image\nLatentSync is best for syncing existing videos to new audio\nRelated Skills\n# Full platform skill (all 150+ apps)\nnpx skills add inference-sh/skills@inference-sh\n\n# Text-to-speech (generate audio for avatars)\nnpx skills add inference-sh/skills@text-to-speech\n\n# Speech-to-text (transcribe for dubbing)\nnpx skills add inference-sh/skills@speech-to-text\n\n# Video generation\nnpx skills add inference-sh/skills@ai-video-generation\n\n# Image generation (create avatar images)\nnpx skills add inference-sh/skills@ai-image-generation\n\n\nBrowse all video apps: infsh app list --category video\n\nDocumentation\nRunning Apps - How to run apps via CLI\nContent Pipeline Example - Building media workflows\nStreaming Results - Real-time progress updates"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/okaris/ai-avatar-video",
    "publisherUrl": "https://clawhub.ai/okaris/ai-avatar-video",
    "owner": "okaris",
    "version": "0.1.5",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ai-avatar-video",
    "downloadUrl": "https://openagent3.xyz/downloads/ai-avatar-video",
    "agentUrl": "https://openagent3.xyz/skills/ai-avatar-video/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-avatar-video/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-avatar-video/agent.md"
  }
}