StepAudio 3 Gen Preview
基于自然语言的统一音频生成：富有表现力的人声，配合音效、环境音、背景音乐和歌唱；限时免费。
规格
- 上下文
- —
- 最大输出
- —
- 输入价
- —
- 输出价
- —
- 发布日期
- —
上下文
- 官方未公布
价格
- 官方未公布
输入输出
- 输入
- 文本音频
- 输出
- 音频
API
- 接口类型
思考
- 官方未公布
源信息
- 状态
- 预览
- 发布日期
- —
- 知识截止
- —
能力
- 官方未公布
调用方式
1 个 Provider
stepfunmodel = stepaudio-3-gen-preview
audio
POSThttps://api.stepfun.ai/v1/audio/generate
JSON
标准格式
{
"id": "stepaudio-3-gen-preview",
"object": "model",
"created": null,
"owned_by": "stepfun",
"name": "StepAudio 3 Gen Preview",
"api": {
"types": [
"audio"
]
},
"limits": {
"context": null,
"input": null,
"output": null
},
"modalities": {
"input": [
"text",
"audio"
],
"output": [
"audio"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": null,
"features": [],
"info": {
"status": "preview",
"release_date": null,
"knowledge_cutoff": null,
"description": "Unified audio generation from natural language: expressive voice with sound effects, ambience, background music and singing; free for a limited time.",
"docs": "https://platform.stepfun.ai/docs/en/guides/models/stepaudio-3-gen",
"verified_at": "2026-10-11"
}
}官方来源
2