同步音频转录

POST

https://router.shengsuanyun.com/api/audio/transcriptions

上传音频（外部 URL）并同步获取转录结果，输出格式由 response_format 控制。

请求参数

Authorization

Bearer Token

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Body 参数application/json必填

示例

{
    "file": "https://example-bucket.oss-cn-beijing.aliyuncs.com/audio/input-01.mp3",
    "model": "whisper-1",
    "response_format": "text",
    "language": "en"
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://router.shengsuanyun.com/api/audio/transcriptions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "file": "https://example-bucket.oss-cn-beijing.aliyuncs.com/audio/input-01.mp3",
    "model": "whisper-1",
    "response_format": "text",
    "language": "en"
}'

返回响应

🟢200成功

application/json

Transcription result. Content-type depends on response_format.

Body

示例

Simple JSON (AudioResponse)Verbose JSON (segments & detailed metadata)

{
    "text": "Hello world. This is the transcript."
}

🟠400请求有误

🟠401未认证

🔴500服务器内部错误

修改于 2025-09-25 10:01:30

Image1图像生成-同步

创建异步转录任务