OpenMOSS-Team/MOSS-TTS-v1.5
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.