Running on Zero 740 IndexTTS 2 Demo π’ 740 Generate expressive speech from text with voice and emotion controls
bosonai/higgs-audio-v2-generation-3B-base Text-to-Speech β’ 6B β’ Updated Jul 28, 2025 β’ 148k β’ 658
Running on CPU Upgrade Featured 1k Model Memory Utility π 1k Calculate VRAM needed for training and inference of HF models