MOSS-TTSD
Multi-speaker dialogue speech generation from character scripts
Community-submitted · content unverified. This organization has not verified ownership or the information in this profile.
About
MOSS-TTSD generates complete multi-speaker conversations from character scripts, with up to five speakers, 20 languages and 60 minutes of audio in one generation. Each character's voice is set from a few seconds of reference audio, with natural turn-taking and overlapping speech for podcasts, audiobooks, dubbing and sports commentary.
- Website
- mosi.cn/en/models/moss-ttsd
- Added via
- web
- Ownership
- unclaimed
Where to go
Product details
- Product kind
- Other