Search
On April 16th, StepFun proudly announced the official launch of its cutting-edge speech generation model, StepAudio 2.5 TTS. This model has undergone significant enhancements in four key areas: global context control, in-text context control, zero-shot voice cloning, and comprehensive voice control. These improvements collectively contribute to a more natural, adaptable, and expressive speech generation experience. StepAudio 2.5 TTS is tailored to cater to a variety of use cases, including character voiceovers, audio content creation, and intelligent voice interactions. It empowers users with the ability to control synthesis through natural language, ensuring straightforward operation and results that closely align with user expectations. Presently, the model is readily accessible on the 'StepFun Open Platform' and through Step Plan.
-
C114 Communication Network -
Communication Home
