What problem does it solve? Choosing and integrating the right AI video generation provider is fragmented across many APIs with different authentication, parameters, and capabilities. This Skill unifies text-to-video and image-to-video generation across multiple gateways (HeyGen, fal.ai, Kling official, Gemini) behind one workflow with provider selection, polling, and fallback guidance. ## Core Features & Use Cases - Multi-Gateway Generation: Access VEO 3.1, Sora V2, Kling, Runway Gen-4, Seedance, MiniMax, and Gemini Omni through four API paths with a single request pattern. - Text-to-Video and Image-to-Video: Submit prompts with optional reference and tail images, aspect ratio control (16:9, 9:16, 1:1), and provider-specific configuration. - Iterative Editing: Use Gemini Omni Flash for stateful multi-turn editing of existing clips, such as restyling, object removal, or lighting changes. - Use Case: A content team needs a 9:16 vertical clip for social media. The Skill submits the prompt to the best available provider, polls the execution endpoint every 10 seconds, and returns the video URL and asset ID. ## Quick Start Ask the agent to generate a 16:9 cinematic video of a drone shot over a coastal city at sunset using the best available configured provider.
