MOSS-TTS
Long-form multilingual speech generation model with zero-shot voice cloning
Community-submitted · content unverified. This organization has not verified ownership or the information in this profile.
About
MOSS-TTS v1.5 is MOSI Intelligence's flagship speech generation model for long-form and multilingual content. It supports 31 languages, zero-shot voice cloning and audio continuation, with fine-grained control over pronunciation, duration and pauses for narration, dubbing and audio content.
- Website
- mosi.cn/en/models/moss-tts
- Added via
- web
- Ownership
- unclaimed
Where to go
Product details
- Product kind
- Other