All models

Step-Audio TTS 3B

StepFun

Text to speech model by StepFun, available through the Foza OpenAI-compatible API.

Text to speech3.5B paramsReleased 2025-02-13Hugging Face

Providers

0

Input from

—

Output from

—

Max context

—

Best latency

—

Tokens processed

0

Providers (0)

Compare price, context and speed across providers serving this model.

No provider serves this model yet.

Specifications

Author
StepFun
Category
Text to speech
Input modalities
Text
Output modalities
Audio
Parameters
3.5B
Max context
—
Released
2025-02-13
Catalog ID
stepfun/step-audio-tts-3b