kling
文字轉音訊
在 CometAPI 中使用 Kling Text to Audio API，將文字 Prompt 轉換為音訊，並支援聲音風格控制、時長選項與可用於串流的輸出。
POST
/
kling
/
v1
/
audio
/
text-to-audio
Create a Kling text-to-audio task
curl --request POST \
--url https://api.cometapi.com/kling/v1/audio/text-to-audio \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "Soft ambient ocean waves at sunrise.",
"duration": 5
}
'{
"code": 0,
"message": "SUCCEED",
"data": {
"task_id": "861254119619698760",
"task_status": "submitted",
"task_info": {},
"created_at": 1773367502225,
"updated_at": 1773367502225
}
}使用此端點可透過 Kling 根據文字 Prompt 產生一段短音訊片段。
呼叫前須知
- 保持
prompt簡潔明確 - 建議先將
duration設定在 3 到 10 秒之間 - 將
callback_url和external_task_id視為可選的整合輔助欄位，而非核心必要項目
任務流程
輪詢任務
透過 Kling 音訊查詢路徑，使用 Individual Queries 持續查詢，直到任務進入最終狀態。
2026-03-13 的即時驗證確認，只包含
prompt 與 duration 的最小請求可被接受，並回傳 task_status: submitted。完整參數參考請見 Kling 官方文件。
授權
Bearer token authentication. Use your CometAPI key.
主體
application/json
Text prompt describing the audio to generate. Max 200 characters.
Duration of the generated audio in seconds. Range: 3.0–10.0, supports one decimal place.
Optional user-defined task ID for your own tracking. Does not replace the system-generated task ID. Must be unique per account.
Webhook URL for task status notifications. The server sends a callback when the task status changes.
⌘I
Create a Kling text-to-audio task
curl --request POST \
--url https://api.cometapi.com/kling/v1/audio/text-to-audio \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"prompt": "Soft ambient ocean waves at sunrise.",
"duration": 5
}
'{
"code": 0,
"message": "SUCCEED",
"data": {
"task_id": "861254119619698760",
"task_status": "submitted",
"task_info": {},
"created_at": 1773367502225,
"updated_at": 1773367502225
}
}