Step Audio 2

Language StepFun Partly verified Released Jul 23, 2025

Step-Audio 2 targets industrial speech applications with a unified model that processes audio directly. Its capabilities include interpreting emotion and speaking style, consulting web search for information, and using audio search to switch voice timbres. Summary written by AI Index from StepFun’s own pages.

  • Reasoning
  • Tool use

Prices

2 offerings · prices as listed
StepFun API (opens in a new tab) Official Global · USD step-audio-2
Conditions/ 1M tokensInputCache readOutput
Standard $1.43$0.29$10.00

Prices from StepFun: pricing details (opens in a new tab) (checked Nov 4, 2026)

StepFun API (opens in a new tab) Official China · CNY step-audio-2
Conditions/ 1M tokensInputCache readOutput
Standard ¥10.00¥2.00¥70.00

Prices from 阶跃星辰:定价明细 (opens in a new tab) (checked Nov 3, 2026)

Standard: the price a request with no conditions pays (the headline price elsewhere on the site).

Details

Built-in tools
Web search
Family
step-audio
Model ID

Not stated on StepFun’s pages: max input, input modalities, output modalities, reasoning efforts, reasoning can be off, max thinking budget, structured output, knowledge cutoff, aliases.

Cited scores

From third-party leaderboards, not measured by us

This model isn’t on any leaderboard we cite yet.

  1. Now priced on StepFun API Input $1.43 · Cache read $0.29 · Output $10.00

Sources

Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data

StepFun · China · stepfun.com

Snapshots, the same family and other models from this provider