StepFunStepAudio 2
Step-Audio 2
Step-Audio 2 understands speech, music, environmental sound and emotion, with tools and search.
Keep the original recording in the task
Practical guidance. This model fits questions about how something sounds as well as what was said. A transcript-only workflow cannot preserve the same evidence about music, environmental sound or vocal expression.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API, Provider product |
| Model identifiers | step-audio-2 |
| Voice options | The Realtime guide lists four built-in voices and custom voice cloning.StepFun Realtime API model support |
| Access | The hosted catalog retains step-audio-2.StepFun billing catalog and 9 November 2026 audio change |
Related models
- Step-Audio 2 Mini
StepFun · StepAudio 2
A speech-dialogue model supporting sound understanding, tool calls and retrieval from text and acoustic material.
Launch date not confirmedAPI · Downloadable - Step-Audio R1.5
StepFun · Step-Audio R
Step-Audio R1.5 adds human-feedback training for natural dialogue while reasoning and speech proceed together.
Launch date not confirmedAPI · Provider product - StepAudio 3 Realtime
StepFun · StepAudio 3
StepAudio 3 Realtime combines audio understanding, turn control, reasoning and tool use.
Launch date not confirmedPreviewAPI · Provider product