Create a text-to-speech response

POST

/v1/text-to-speech

Runs the text-to-speech contract and returns generated audio metadata. Phase 14 uses this boundary to meter TTS provider usage outside the CNY 500/month infra cap.

请求参数

Body 参数application/json必填

示例

{
    "text": "Read this note aloud.",
    "voice": "longwan",
    "locale": "en-US",
    "audioFormat": "mock-audio"
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/text-to-speech' \
--header 'Content-Type: application/json' \
--data '{
    "text": "Read this note aloud.",
    "voice": "longwan",
    "locale": "en-US",
    "audioFormat": "mock-audio"
}'

返回响应

🟢200成功

application/json

Text-to-speech completed.

Bodyapplication/json

示例

{
    "endpoint": "POST /v1/text-to-speech",
    "result": {
        "audioFormat": "mock-audio",
        "audioData": "b25lc2F5LWRldGVybWluaXN0aWMtdHRz",
        "audioSeconds": 1.75,
        "ttsCharacters": 21,
        "voice": "longwan",
        "locale": "en-US",
        "generatedAt": "2026-04-26T06:00:00Z"
    }
}

修改于 2026-08-26 04:04:36

Create an ask-anything response

Read usage ledger entries