MiniMax releases H3 open-weight omni-modal video model
MiniMax H3 is a 33B-parameter open-weight model generating video with native stereo audio up to 2K and 15 seconds. It supports text, image, video, and audio inputs, with Day 0 support in ComfyUI, fal, and Vercel AI Gateway.
How this story unfolded
4 weeks · 4 reports · 39 community posts · 43 of 54 shown
- Jul 31
- Aug 1
- Aug 2
- Aug 3
- Aug 4
- Aug 5
- Aug 10
- Aug 11
- Aug 13
- Aug 25
- Aug 26
- Aug 27
MiniMax by email
Get an email when MiniMax has news
No news that day, no email.
More stories today
- SentinelOne CEO discusses earnings and AI's cybersecurity impact
- Andrew Ng: Biggest AI opportunities aren't where you think
- OpenAI co-founder warns of closing window to secure internet
- Yann LeCun: Provably safe AI is impossible
- Gemini 3.8 Flash preview reportedly in use at Google