Skip to content
Inteligencia IAAug 21, 2026Inteligencia IA
Artigo

MiniMax released open weights for H3, a model that fuses text, image, video, and audio as context and outputs native stereo sound...

Up to 15 seconds at 2K. Community benchmarks show the 768p Base model running on consumer GPUs in minutes.

Editorial Data Cube AIFonte: Pandaily
01

Brief da fonte

MiniMax released open weights for H3, a model that fuses text, image, video, and audio as context and outputs native stereo sound up to 15 seconds at 2K. Community benchmarks show the 768p Base model running on consumer GPUs in minutes.