{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ai-video-gen",
    "name": "Ai Video Gen",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/rhanbourinajd/ai-video-gen",
    "canonicalUrl": "https://clawhub.ai/rhanbourinajd/ai-video-gen",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ai-video-gen",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-video-gen",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "add_voiceover.py",
      "generate_video.py",
      "images_to_video.py",
      "QUICK_START.md",
      "README.md",
      "requirements.txt"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "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-video-gen"
    },
    "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-video-gen",
    "agentPageUrl": "https://openagent3.xyz/skills/ai-video-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-video-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-video-gen/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": "AI Video Generation Skill",
        "body": "Generate complete videos from text descriptions using AI."
      },
      {
        "title": "Capabilities",
        "body": "Image Generation - DALL-E 3, Stable Diffusion, Flux\nVideo Generation - LumaAI, Runway, Replicate models\nVoice-over - OpenAI TTS, ElevenLabs\nVideo Editing - FFmpeg assembly, transitions, overlays"
      },
      {
        "title": "Quick Start",
        "body": "# Generate a complete video\npython skills/ai-video-gen/generate_video.py --prompt \"A sunset over mountains\" --output sunset.mp4\n\n# Just images to video\npython skills/ai-video-gen/images_to_video.py --images img1.png img2.png --output result.mp4\n\n# Add voiceover\npython skills/ai-video-gen/add_voiceover.py --video input.mp4 --text \"Your narration\" --output final.mp4"
      },
      {
        "title": "Required API Keys",
        "body": "Add to your environment or .env file:\n\n# Image Generation (pick one)\nOPENAI_API_KEY=sk-...              # DALL-E 3\nREPLICATE_API_TOKEN=r8_...         # Stable Diffusion, Flux\n\n# Video Generation (pick one)\nLUMAAI_API_KEY=luma_...           # LumaAI Dream Machine\nRUNWAY_API_KEY=...                # Runway ML\nREPLICATE_API_TOKEN=r8_...        # Multiple models\n\n# Voice (optional)\nOPENAI_API_KEY=sk-...             # OpenAI TTS\nELEVENLABS_API_KEY=...            # ElevenLabs\n\n# Or use FREE local options (no API needed)"
      },
      {
        "title": "Install Dependencies",
        "body": "pip install openai requests pillow replicate python-dotenv"
      },
      {
        "title": "FFmpeg",
        "body": "Already installed via winget."
      },
      {
        "title": "1. Text to Video (Full Pipeline)",
        "body": "python skills/ai-video-gen/generate_video.py \\\n  --prompt \"A futuristic city at night with flying cars\" \\\n  --duration 5 \\\n  --voiceover \"Welcome to the future\" \\\n  --output future_city.mp4"
      },
      {
        "title": "2. Multiple Scenes",
        "body": "python skills/ai-video-gen/multi_scene.py \\\n  --scenes \"Morning sunrise\" \"Busy city street\" \"Peaceful night\" \\\n  --duration 3 \\\n  --output day_in_life.mp4"
      },
      {
        "title": "3. Image Sequence to Video",
        "body": "python skills/ai-video-gen/images_to_video.py \\\n  --images frame1.png frame2.png frame3.png \\\n  --fps 24 \\\n  --output animation.mp4"
      },
      {
        "title": "Budget Mode (FREE)",
        "body": "Image: Stable Diffusion (local or free API)\nVideo: Open source models\nVoice: OpenAI TTS (cheap) or free TTS\nEdit: FFmpeg"
      },
      {
        "title": "Quality Mode (Paid)",
        "body": "Image: DALL-E 3 or Midjourney\nVideo: Runway Gen-3 or LumaAI\nVoice: ElevenLabs\nEdit: FFmpeg + effects"
      },
      {
        "title": "Scripts Reference",
        "body": "generate_video.py - Main end-to-end generator\nimages_to_video.py - Convert image sequence to video\nadd_voiceover.py - Add narration to existing video\nmulti_scene.py - Create multi-scene videos\nedit_video.py - Apply effects, transitions, overlays"
      },
      {
        "title": "API Cost Estimates",
        "body": "DALL-E 3: ~$0.04-0.08 per image\nReplicate: ~$0.01-0.10 per generation\nLumaAI: $0-0.50 per 5sec (free tier available)\nRunway: ~$0.05 per second\nOpenAI TTS: ~$0.015 per 1K characters\nElevenLabs: ~$0.30 per 1K characters (better quality)"
      },
      {
        "title": "Examples",
        "body": "See examples/ folder for sample outputs and prompts."
      }
    ],
    "body": "AI Video Generation Skill\n\nGenerate complete videos from text descriptions using AI.\n\nCapabilities\nImage Generation - DALL-E 3, Stable Diffusion, Flux\nVideo Generation - LumaAI, Runway, Replicate models\nVoice-over - OpenAI TTS, ElevenLabs\nVideo Editing - FFmpeg assembly, transitions, overlays\nQuick Start\n# Generate a complete video\npython skills/ai-video-gen/generate_video.py --prompt \"A sunset over mountains\" --output sunset.mp4\n\n# Just images to video\npython skills/ai-video-gen/images_to_video.py --images img1.png img2.png --output result.mp4\n\n# Add voiceover\npython skills/ai-video-gen/add_voiceover.py --video input.mp4 --text \"Your narration\" --output final.mp4\n\nSetup\nRequired API Keys\n\nAdd to your environment or .env file:\n\n# Image Generation (pick one)\nOPENAI_API_KEY=sk-...              # DALL-E 3\nREPLICATE_API_TOKEN=r8_...         # Stable Diffusion, Flux\n\n# Video Generation (pick one)\nLUMAAI_API_KEY=luma_...           # LumaAI Dream Machine\nRUNWAY_API_KEY=...                # Runway ML\nREPLICATE_API_TOKEN=r8_...        # Multiple models\n\n# Voice (optional)\nOPENAI_API_KEY=sk-...             # OpenAI TTS\nELEVENLABS_API_KEY=...            # ElevenLabs\n\n# Or use FREE local options (no API needed)\n\nInstall Dependencies\npip install openai requests pillow replicate python-dotenv\n\nFFmpeg\n\nAlready installed via winget.\n\nUsage Examples\n1. Text to Video (Full Pipeline)\npython skills/ai-video-gen/generate_video.py \\\n  --prompt \"A futuristic city at night with flying cars\" \\\n  --duration 5 \\\n  --voiceover \"Welcome to the future\" \\\n  --output future_city.mp4\n\n2. Multiple Scenes\npython skills/ai-video-gen/multi_scene.py \\\n  --scenes \"Morning sunrise\" \"Busy city street\" \"Peaceful night\" \\\n  --duration 3 \\\n  --output day_in_life.mp4\n\n3. Image Sequence to Video\npython skills/ai-video-gen/images_to_video.py \\\n  --images frame1.png frame2.png frame3.png \\\n  --fps 24 \\\n  --output animation.mp4\n\nWorkflow Options\nBudget Mode (FREE)\nImage: Stable Diffusion (local or free API)\nVideo: Open source models\nVoice: OpenAI TTS (cheap) or free TTS\nEdit: FFmpeg\nQuality Mode (Paid)\nImage: DALL-E 3 or Midjourney\nVideo: Runway Gen-3 or LumaAI\nVoice: ElevenLabs\nEdit: FFmpeg + effects\nScripts Reference\ngenerate_video.py - Main end-to-end generator\nimages_to_video.py - Convert image sequence to video\nadd_voiceover.py - Add narration to existing video\nmulti_scene.py - Create multi-scene videos\nedit_video.py - Apply effects, transitions, overlays\nAPI Cost Estimates\nDALL-E 3: ~$0.04-0.08 per image\nReplicate: ~$0.01-0.10 per generation\nLumaAI: $0-0.50 per 5sec (free tier available)\nRunway: ~$0.05 per second\nOpenAI TTS: ~$0.015 per 1K characters\nElevenLabs: ~$0.30 per 1K characters (better quality)\nExamples\n\nSee examples/ folder for sample outputs and prompts."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/rhanbourinajd/ai-video-gen",
    "publisherUrl": "https://clawhub.ai/rhanbourinajd/ai-video-gen",
    "owner": "rhanbourinajd",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ai-video-gen",
    "downloadUrl": "https://openagent3.xyz/downloads/ai-video-gen",
    "agentUrl": "https://openagent3.xyz/skills/ai-video-gen/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-video-gen/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-video-gen/agent.md"
  }
}