MiniMax Releases MiniMax H3: An Omni-Modal Video Model That Generates 15-Second 2K Clips With Native Stereo Audio

MiniMax has launched MiniMax H3, a multimodal model capable of generating 15-second, 2K resolution video clips accompanied by native stereo audio. Unlike systems that rely on modular components for sound, this model processes text, images, video, and audio within a unified framework. This integration aims to improve synchronization between visual content and its corresponding audio output.