MiniMax H3: SOTA open video model with native audio
MiniMax H3 generates 15-second 2K video clips with native stereo audio, reading text, images, video, and audio as one unified context. It is now the SOTA open video generation model on both @arena and @ArtificialAnlys benchmarks, with open weights enabling community ports to Mac and gaming GPUs.
How this story unfolded
3 weeks · 2 reports · 146 community posts · 148 of 150 shown
- Jul 31
- Aug 1
- Aug 2
- Aug 3
- Aug 4
- Aug 5
- Aug 6
- Aug 7
- Aug 8
- Aug 9
- Aug 10
- Aug 11
- Aug 12
- Aug 13
- Aug 14
- Aug 15
- Aug 16
- Aug 17
- Aug 18
- Aug 19
- Aug 20
- Aug 21
MiniMax by email
Get an email when MiniMax has news
No news that day, no email.
More stories today
- Simile AI raises $2B Series B for human behavior simulation
- ChatGPT adds recent photos shortcut and time features
- Best GPU Neoclouds 2026: CoreWeave, Nebius, Lambda, Crusoe, Groq Ranked
- Anthropic's Opus 4.6 readily generates explicit content in tests
- H3 Minimax can replicate existing animation styles