Spaces:
Running
Running
| name: Multi-Speaker Dialogue Generation | |
| description: Demos showcasing multi-speaker dialogue synthesis. Unlike existing dialogue synthesis models, ours supports instruction-based control, with demos presented both with and without instructions. | |
| models: | |
| - MOSS-TTSD-V1 | |
| - SoulX-Podcast | |
| - Ours(without instruction) | |
| - Ours(with instruction) | |