The OpenMOSS team has released MOSS-TTS-v1.5, an updated version of their text-to-speech model. This new version builds upon the capabilities of MOSS-TTS 1.0, introducing enhanced multilingual synthesis with language tags, more stable voice cloning for improved speaker similarity, and better handling of long-reference, short-text cloning scenarios. MOSS-TTS-v1.5 also offers more stable punctuation-following prosody and introduces explicit pause control using inline markers. AI
IMPACT Enhances multilingual synthesis and voice cloning capabilities for open-source TTS.
RANK_REASON This is a release of a new version of an open-source text-to-speech model, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Hugging Face Trending Models →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →