88Z AI, 16 April — StepFun has released the new StepAudio 2.5 TTS voice generation model, featuring global and in-text context control along with zero-shot cloning. Users can precisely adjust voice details via natural language, enabling a shift from mere voice reproduction to creative expression, while supporting high-quality speech generation for any voice without retraining.
At a glance
- Supports precise control of voice emotion and rhythm details via natural language
- Features zero-shot cloning for any voice timbre without retraining
The update
StepFun has officially launched StepAudio 2.5 TTS, a new-generation voice generation model. It features three core capabilities: global context control, in-text context control, and zero-shot cloning. With these features, users can precisely adjust details such as emotional tone, rhythm, pauses, and stress using natural language. This technological breakthrough enables a leap from simply reproducing voices to creatively expressing them. Furthermore, the model supports zero-shot cloning for any voice timbre, allowing high-quality speech generation without the need for retraining, thereby significantly enhancing the flexibility and efficiency of voice production.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 阶跃星辰Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.