All activity
MiniMax Audio Teamstarted a discussion
MiniMax Speech-02-HD: Zero-Shot, Multilingual, Cost-Effective TTS
What sets MiniMax apart: → Zero-shot speaker cloning using raw audio (no transcripts required) → Flow-VAE model: no spectrograms needed, enabling faster and more natural speech → Multilingual and cross-lingual synthesis (supports Thai, Vietnamese, Cantonese, etc.) → Ranked #1 on Artificial Arena’s public TTS leaderboard → Emotion control via LoRA + T2V (text-to-voice from plain textual...