Happy Horse 1.1 generates cinematic video with synchronized native audio and multilingual lip-sync from a text prompt or an optional first-frame image. Clips run 3 to 15 seconds at 720p or 1080p in nine aspect ratios from 16:9 to 21:9. Describe scene, camera movement, dialogue, and ambience in one prompt; the model writes speech and sound together. Ideal for social ads, game cinematics, product demos, broadcast talking heads, and image-to-video motion from a still.