StepFunStep TTS
Step TTS 2
Step TTS 2 uses next-token prediction without separate speaker or emotion embeddings.
Reuse the earlier voice set
Step TTS 2 retains Mini's voices and control options.StepFun audio model overview
Check old prompts with the new voice
Practical guidance. Voice compatibility does not establish identical pronunciation or pacing. Listen to names, numbers and long pauses from existing scripts when moving from Mini to this release.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | step-tts-2 |
| Voice range | The audio guide lists 11 emotion and 17 style controls.StepFun audio model overview |
| Access | The speech endpoint lists step-tts-2 as a supported model.StepFun speech synthesis API |
Related models
- Step TTS Mini
StepFun · Step TTS
Step TTS Mini is an earlier hosted speech synthesis model with voice cloning and emotion or style controls.
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 - StepAudio 3 TTS
StepFun · StepAudio 3
StepAudio 3 TTS produces speech from text and reference audio.
Launch date not confirmedAPI · Provider product