Step-1o Audio
Step-1o Audio is StepFun's first-generation end-to-end voice model. The public catalog lists speech interaction and tool calling, with sessions lasting up to 30 minutes.
Use the session protocol
Realtime handles voice activity detection, conversation state and tool definitions through session events. Step-1o Audio remains an option in that protocol.StepFun Realtime API model support
Retain a reference conversation
Practical guidance. For an existing device integration, save an evaluation script that covers interruptions, tool results and session duration. This gives a useful comparison when considering the newer Audio 3 model.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | step-1o-audio |
| Input and output | The Realtime API accepts speech or text input and can return audio.StepFun Realtime API model support |
| Access | The current Realtime API and billing catalog retain step-1o-audio.StepFun Realtime API model supportStepFun billing catalog and 9 November 2026 audio change |
Related models
- StepAudio 2.5 Realtime
StepFun · StepAudio 2.5
StepAudio 2.5 Realtime accepts and returns speech over WebSocket.
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