文生音频

POST

/ent/v2/text2audio

根据文本描述生成音频

请求参数

Authorization

API Key

在 header 添加参数

Authorization

示例：

Authorization: ********************

Body 参数application/json必填

示例

{
    "model": "audio1.0",
    "prompt": "轻柔的钢琴曲",
    "duration": 5
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST '/ent/v2/text2audio' \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "audio1.0",
    "prompt": "轻柔的钢琴曲",
    "duration": 5
}'

返回响应

🟢200成功

application/json

任务创建成功

Body

示例

{
    "task_id": "string",
    "state": "pending",
    "model": "string",
    "prompt": "string",
    "images": [
        "string"
    ],
    "duration": 0,
    "seed": 0,
    "resolution": "string",
    "bgm": true,
    "movement_amplitude": "string",
    "payload": "string",
    "off_peak": true,
    "credits": 0,
    "watermark": true,
    "created_at": "2019-08-24T14:15:22.123Z"
}

修改于 2025-10-29 13:35:00

参考生图

可控文生音效