StepAudio 2.5 TTS

Text to speech StepFun Verified

StepAudio 2.5 TTS is a speech synthesis model for audiobooks, short drama dubbing, advertising narration and emotional storytelling. It accepts natural language directions to set the overall scene and control delivery within sentences, and supports voice cloning from reference audio. 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) Official Global · USD stepaudio-2.5-tts
Conditions/ 1M charactersCharacter
Standard $85.00

Prices from StepFun: pricing details (opens in a new tab) (checked Nov 9, 2026)

StepFun API (opens in a new tab) Official China · CNY stepaudio-2.5-tts
Conditions/ 1M charactersCharacter
Standard ¥580.00

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 us

No cited leaderboard covers speech synthesis yet. We will cite one when its license allows.

  1. 1 new price on StepFun API, China Character ¥580.00

Sources

StepFun · China · stepfun.com

Snapshots, the same family and other models from this provider