Step TTS Mini
Step TTS Mini is an earlier hosted speech synthesis model with voice cloning and emotion or style controls. The public catalog lists Chinese, English, Japanese, Cantonese and Sichuanese output.
Keep label controls separate from natural-language controls
The speech API supports the Mini model through its voice-label controls. Language, emotion and style cannot all be set together in that field.StepFun speech synthesis API
Check whether one control is sufficient
Practical guidance. A short notification may need one language or style setting. A dramatic passage may need more detailed direction. Compare Contextual TTS releases when the same sentence needs several changes in delivery.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | step-tts-mini |
| Text limit | Up to 1,000 input characters per speech request.StepFun speech synthesis API |
| Voice control | The guide describes voice cloning from about ten seconds of reference audio.StepFun audio model overview |
Related models
- Step TTS 2
StepFun · Step TTS
A speech-synthesis model that uses next-token prediction without separate speaker or emotion embeddings.
Launch date not confirmedAPI - StepAudio 2.5 TTS
StepFun · StepAudio 2.5
StepAudio 2.5 TTS uses overall context and inline directions to control a voice performance.
Launch date not confirmedAPI · Provider product