ChipsHacker Noonabout 5 hours ago
Audio8-TTS-Preview-0.6B: Compact Multilingual Voice Cloning
10 min read
Audio8-TTS-Preview-0.6B is a 0.6B-parameter multilingual text-to-speech model with zero-shot voice cloning, using a DualAR architecture and 44.1 kHz codec. It supports 11 languages and achieves state-of-the-art-class performance on multilingual benchmarks despite its compact size. The model requires Python 3.10+ and a CUDA-capable GPU.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
