MiniMax H3 Video Model Launches with Native Stereo Audio and Multimodal References

smtabatabaie · x · 2026-07-31

Hailuo AI (MiniMax) has released its next-generation multimodal video model, H3, now available Day 0 on the Scenario platform.

The model features robust multimodal inputs and native stereo audio generation. Users can leverage text, images (including first and last frames), and up to 9 images, 3 videos, and 3 audio clips as references, maintaining high consistency throughout. It also supports 2K resolution, 7000-character prompts, and 15-second videos at 24 FPS.

Related event: MiniMax Launches Omni-Modal Model H3 with Native 2K Stereo Video(17 posts)→

Original post →

More from Models

Models channel →