Black Forest Labs releases Flux 3, a multimodal model that generates video with native audio

Black Forest Labs has released Flux 3, a multimodal foundation model that learns from images, video, and audio and can generate video with native sound for the first time. The model can generate videos up to 20 seconds long. Black Forest Labs' own tests put Flux 3 just ahead of market leader Sora from OpenAI, though independent results are not yet available. The company is already testing Flux 3 on robotics tasks as part of its broader goal to build a world model.