Features
-
Highly realistic, multilingual speech generation
-
generate music, background noise and simple sound effects
-
Production of nonverbal communications like laughing, sighing and crying
-
Access to pretrained model checkpoints ready for inference
-
Support for the research community
Good For
-
Multilingual audiobooks and podcasts
-
Background noise and sound effects for films, TV shows and video games
-
Assistive technology for individuals with speech impairments
-
Text-to-speech technology
