ModelInfo
English
All models

StepAudio 2.5 TTS

Context-aware text-to-speech with natural-language delivery control and zero-shot voice cloning.

StepFunstepaudio-2.5-ttsReport incorrect data

Specs

Context
—
Max output
—
Input price
$85/ 1M characters
Output price
—
Released
—

Context

Not published

Pricing · USD / 1M characters

Input
$85
Output
—
Cache read
—
Cache write
—

Modalities

Input
Text
Output
Audio

API

API types
audio

Reasoning

Not published

Info

Status
Active
Released
—
Knowledge cutoff
—

Features

Not published
Source · official docsVerified 2026-10-11

How to call

1 provider

stepfunmodel = stepaudio-2.5-tts

audio
POSThttps://api.stepfun.ai/v1/audio/speech

JSON

Standard format
stepaudio-2.5-tts.json
{
  "id": "stepaudio-2.5-tts",
  "object": "model",
  "created": null,
  "owned_by": "stepfun",
  "name": "StepAudio 2.5 TTS",
  "api": {
    "types": [
      "audio"
    ]
  },
  "limits": {
    "context": null,
    "input": null,
    "output": null
  },
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "audio"
    ]
  },
  "reasoning": {
    "supported": null,
    "efforts": []
  },
  "pricing": {
    "currency": "USD",
    "unit": "1M_characters",
    "input": 85,
    "output": null,
    "cache_read": null,
    "cache_write": null
  },
  "features": [],
  "info": {
    "status": "active",
    "release_date": null,
    "knowledge_cutoff": null,
    "description": "Context-aware text-to-speech with natural-language delivery control and zero-shot voice cloning.",
    "docs": "https://platform.stepfun.ai/docs/en/guides/models/stepaudio-2.5-tts",
    "verified_at": "2026-10-11"
  }
}

Official sources

4