Step TTS 2
Step TTS 2 is StepFun’s text-to-speech upgrade to Step TTS Mini, intended for expressive dubbing and dialogue. It uses pure next-token prediction without separate speaker or emotion embedding modules, while retaining Mini’s voices, emotions, styles and languages. Summary written by AI Index from StepFun’s own pages.
- Voice cloning
- Streaming
Prices
2 offerings · prices as listed StepFun API (opens in a new tab)
step-tts-2| Conditions/ 1M characters | Character |
|---|---|
| Standard | $40.00 |
Prices from StepFun: pricing details (opens in a new tab) (checked Nov 9, 2026)
StepFun API (opens in a new tab)
step-tts-2| Conditions/ 1M characters | Character |
|---|---|
| Standard | ¥280.00 |
Prices from 阶跃星辰:定价明细 (opens in a new tab) (checked Nov 7, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Max input
- 1,000
- Model ID
Cited scores
From third-party leaderboards, not measured by usNo cited leaderboard covers speech synthesis yet. We will cite one when its license allows.
Changes
All changes →- 1 new price on StepFun API, China Character ¥280.00
Sources
- 阶跃星辰:定价明细in Chinese (opens in a new tab) platform.stepfun.com · checked Nov 7, 2026
- 阶跃星辰:语音模型in Chinese (opens in a new tab) platform.stepfun.com · checked Nov 9, 2026
- 阶跃星辰 API:流式语音合成in Chinese (opens in a new tab) platform.stepfun.com · checked Nov 9, 2026
- 阶跃星辰 API:复刻音色in Chinese (opens in a new tab) platform.stepfun.com · checked Nov 9, 2026
- StepFun: pricing details (opens in a new tab) platform.stepfun.ai · checked Nov 9, 2026
StepFun · China · stepfun.com
Related models
Snapshots, the same family and other models from this provider