Step TTS 2 audio
stepfun-ai/step-tts-2 · family step · in: text → out: audio · price provider-declared (via models.dev). Capabilities: text.
This is an audio model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See StepFun (Global)’s docs for per-unit rates.
- Provider
- StepFun (Global) (
stepfun-ai) - Kind
- audio (outputs audio)
- Context
- 0 tokens
- Max output
- 0 tokens
- Capabilities
- text
Call it
jishie indexes & prices models; it does not proxy inference.
Audio generation — call StepFun (Global)’s audio API with model id step-tts-2. Endpoints vary by provider; see their docs.
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):