What problem does it solve? Creating video content from scratch requires filming, editing, and production resources. This Skill lets you generate AI videos directly from text prompts or reference images through multiple provider gateways, without managing separate API integrations for each video model. ## Core Features & Use Cases - Multi-Provider Video Generation: Access VEO, Kling, Sora, Runway, Seedance, MiniMax, and LTX models through the HeyGen and fal.ai gateways with a single workflow API. - Text-to-Video and Image-to-Video: Generate clips from text descriptions or animate reference images, with control over aspect ratio (16:9, 9:16, 1:1) and provider-specific configuration. - Async Job Management: Submit generation requests, receive an execution ID, and poll for completion to retrieve the video URL and asset ID. - Use Case: A social media team needs a vertical 9:16 clip of a coffee shop interior for a reel. Submit the prompt with the desired aspect ratio, poll the execution endpoint, and download the finished video. ## Quick Start Ask the agent to generate a 16:9 video of a drone shot flying over a coastal city at sunset using the default provider.
