Towards Scalable Pre-training of Visual Tokenizers for Generation Paper • 2512.13687 • Published Dec 15, 2025 • 102
Running 103 MiniMax Speech Tech Report 🎙 103 Generate high-quality speech from text with voice cloning
MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder Paper • 2505.07916 • Published May 12, 2025 • 134