StepStar has released the speech generation model StepAudio 2.5 TTS.
On April 16th, StepStar announced the official release of its new generation speech generation model, StepAudio 2.5 TTS. Focusing on three core capabilities - global context control, in-text context control, zero-sample replication, and full-tone control - this model enables more natural, flexible and expressive speech generation
.