Founded in early 2022, MiniMax is driven by the mission to 'co-create intelligence with everyone,' dedicated to advancing the frontiers of AI and achieving Artificial General Intelligence (AGI). MiniMax has independently developed a series of multimodal foundation models with powerful code and Agent capabilities, as well as ultra-long context processing, capable of understanding, generating, and integrating multiple modalities including text, audio, image, video, and music.
This is the 10th launch from MiniMax. View more
MiniMax H3
Launched this week
MiniMax H3 is an open multimodal model that generates 2K video with native stereo sound. It unifies text, image, and audio inputs, excelling at accurate text rendering, visual packaging, and complex instruction following for commercial content creation.
Free Options
Launch Team
Will be it free or paid or freemium?
TapRefer
thanks for eating my job. lol
Creatium
The multimodal breadth here is impressive: text, audio, image, video, and music under one roof is a lot to pull off well, and the ultra-long context plus strong code/agent capabilities is exactly the combination that makes these models actually useful for real workflows rather than demos. "Co-create intelligence with everyone" is a nice framing for the mission too. Curious which modality you've found resonates most with builders so far. Congrats on the launch! 🚀
ongrats on the launch, this is a strong day one showing. Mixing text, image and audio inputs in one model would make quick brand teasers way less painful, right now that is three tools and a lot of glue between them. Can I feed it a product shot plus a rough voiceover clip and have it build the motion design around both?