ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
MiniMax released MiniMax-Music3, an open-weights text-to-music model generating complete songs up to five minutes from lyrics and a structured caption. It outputs 32 kHz, 16-bit stereo WAV using a Hybrid-LM with 8B Global and 0.6B Local LLMs. Weights, inference code, and three serving paths shipped.
Tap to vote and see what everyone thinks.
Summary by ByteBrief