STORY · MODELLER_

MiniMax H3: omni-modal generative AI model for video, audio and text

MiniMax has launched H3, a generative AI model that understands and generates content across text, images, video and audio. The model can produce video in up to 2K resolution with stereo audio, and is now available on Hugging Face as well as via API and web apps globally.

WHY IT MATTERS

H3 represents a significant expansion of multimodal AI capability, particularly for video generation with complex context understanding. It marks intensifying competition in video AI among major players.

SOURCES

MACHINE-GENERATED SUMMARY This summary is written by machine from the sources below. We sort and explain — but we are a way into the field, not the final word. Check the source when something matters to you.