DEVOURED
MiniMax H3
MiniMax has released H3, a new open-weights multimodal model capable of generating video and audio alongside text.
What: MiniMax H3 is a unified context model that processes text, image, video, and audio. It features 2K video generation up to 15 seconds, native stereo audio, and commercial-grade instruction following.
Why it matters: The rapid emergence of capable, multimodal open-weights models is standardizing advanced generation capabilities, shifting the competitive focus toward cost and integration efficiency.
Decoder
- Multimodal: A model capable of processing and generating multiple types of data (e.g., text, audio, video) in a single integrated workflow.
Original article
Full article content is not available for inline reading.
Explore all 58 articles in today's digest
Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi