Generate videos via Veo 3.1, Kling 3.0, or Sora 2 backends.
npx skills add https://github.com/cgk-platform/cgk --skill veo-video-gen
Please help me install this Agent Skill. Skill: veo-video-gen Source: https://github.com/cgk-platform/cgk/tree/main/openclaw-skills/veo-video-gen Command: npx skills add https://github.com/cgk-platform/cgk --skill veo-video-gen
Streamline end-to-end AI-generated video creation by coordinating Veo 3.1, Kling 3.0, and Sora 2 backends from a single workflow, with support for text-to-video and image-to-video, configurable duration, aspect ratio, and resolution, plus multi-video output and Slack uploads.
Initiate a video generation with a prompt and output path, then review the resulting media after completion.
High-intent search queries and answers about installing and using this skill.
You can generate AI videos across Veo 3.1, Kling 3.0, or Sora 2 by submitting text prompts or reference images. The workflow automates backend orchestration, allowing configurable duration, aspect ratio, and resolution for text-to-video and image-to-video outputs.
Yes, you can automate Slack distribution for AI-generated videos. The workflow supports multi-video output and Slack uploads, generating .meta.json sidecars to facilitate downstream automation and marketing distribution.
Yes, the video generation workflow uses automatic backend fallback to maximize uptime. It transitions sequentially from vertex-veo-fast to veo-fast, kling-pro, and sora backends to ensure successful text-to-video and image-to-video completion.
You extend video duration for marketing and training demonstrations using the built-in extension workflows. This feature lengthens generated clips via Kling, Veo, or Sora backends, supporting multi-video output and configurable parameters.
For text-to-video and image-to-video generation, you can configure duration, aspect ratio, resolution, and audio settings. The workflow applies these parameters across Veo 3.1, Kling 3.0, and Sora 2 backends while managing metadata.
nunomenGenerate and edit images from natural language prompts via the Gemini API.
phuhao00Optimize short-video content for Douyin and TikTok recommendation algorithms.
haposoftAnalyze and generate images, audio, video, and documents via Gemini API and Imagen 4.
yonatangrossProcess images, transcribe audio, generate speech, and create videos with multimodal AI models.
