MOSS-TTS-v1.5 Tops Hugging Face Trending for Text-to-Speech
MOSS-TTS-v1.5, a multilingual controllable text-to-speech model by OpenMOSS-Team, has reached #1 on Hugging Face Trending among TTS models with 20.6K downloads. The model supports stable voice cloning, long-form audio generation, precise pause control, and multiple languages. It is now officially supported in vLLM-Omni and SGLang-Omni, making it viable for production voice applications beyond experimentation.