ByteDance Seed 2

AI generator for dialogue, music, ambience, and sound effects Seed Audio 1.0 is ByteDance Seed's multimodal AI audio generation model for creating complete sound scenes from text, images, or audio references. It can generate multi-speaker dialogue, emotional delivery, native accents, ambience, background music, and foley-style sound effects in a single prompt. The platform is designed for longer audio scenes and supports layer-aware output for creative projects such as films, advertisements, podcasts, games, education, and XR prototypes.

Multimodal AI generator for 15s multi-shot clips with synced audio and stable motion. Seedance AI features the SEEDANCE 2 AI Video Generator, a next-generation multimodal audio-video model developed by ByteDance Seed. It utilizes a unified architecture to generate 15-second multi-shot video clips with perfectly synced dual-channel audio from text, image, audio, and video inputs. The model is designed for high motion stability, physical accuracy, and visual realism, allowing creators to steer the look and rhythm of scenes using up to 9 image references, 3 video clips, and 3 audio clips simultaneously.