MiniMax H3 Max tops video leaderboards with native audio support
gorkem · x · 2026-08-28
MiniMax H3 Max, a post-trained variant of MiniMax H3 built and served by fal, is now available via API.
Performance:
- Debuts at #1 in Image-to-Video with Audio and #3 in Text-to-Video with Audio on the Artificial Analysis Video Leaderboards.
- Outperforms the base MiniMax H3 and ByteDance's Dreamina Seedance 2.0 in the Image-to-Video category.
Features:
- Tuned for stronger prompt adherence and better aesthetics.
- Co-optimized with fal's custom inference stack for higher throughput.
- Generates 5 to 15-second clips with native audio at up to 768p resolution.
More from Multimodal
- Google adds video reference input to multimodal models for character consistency — shlomifruchter · 2026-08-28
- AI music video created with cloned voice and agentic tools — Kyrannio · 2026-08-28
- Synthesia Reaches $4B Valuation, Pivots AI Video to Interactive Agents — alexvoica · 2026-08-28
- ElevenLabs launches Music v2 model for studio-quality audio generation — lukeharries · 2026-08-28
- AI art project Remanence launches: reconstructing memories via neural networks — bushibuilds · 2026-08-28
- Prompt for generating motion-style images of Timothée Chalamet in Midjourney — michaelrabone · 2026-08-28