All Models
Step TTS 2
Speech generation model for controllable voice, narration, and audio delivery
Available Providers (2)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 StepFun (Global) | step-tts-2 | —/MTok | —/MTok | — | — | |
 StepFun (China) | step-tts-2 | —/MTok | —/MTok | — | — |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output