音频（Audio）原生OpenAI格式
文本转语音
将文本转换为音频
Request Body
application/json
model*string
模型名称，需与模型广场中的标识完全一致
input*string
要转换的文本
Length
length <= 4096voice*string
音色
Value in
"alloy" | "echo" | "fable" | "onyx" | "nova" | "shimmer"response_format?string
返回格式。设为 json_schema 可启用结构化输出，强制匹配给定 Schema
Default
"mp3"Value in
"mp3" | "opus" | "aac" | "flac" | "wav" | "pcm"speed?number
语速倍率，0.25–4.0，默认 1.0
Default
1Range
0.25 <= value <= 4Response Body
audio/mpeg
curl -X POST "https://jiniu.ai/v1/audio/speech" \ -H "Content-Type: application/json" \ -d '{ "model": "tts-1", "input": "string", "voice": "alloy" }'"string"