kling
创建对口型任务
通过 CometAPI Kling POST /kling/v1/videos/advanced-lip-sync 创建高级对口型视频任务，提交音频和对口型设置以生成同步结果。
POST
/
kling
/
v1
/
videos
/
advanced-lip-sync
Create an advanced Kling lip-sync task
curl --request POST \
--url https://api.cometapi.com/kling/v1/videos/advanced-lip-sync \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"session_id": "806556222048190514",
"face_choose": [
{
"face_id": "0",
"sound_file": "https://cdn1.suno.ai/e5c97078-3260-4354-a3a6-1d7249262a48.mp3",
"sound_start_time": "1200",
"sound_end_time": "5000",
"sound_insert_time": "0"
}
]
}
'{
"code": 123,
"message": "<string>",
"data": {
"task_id": "<string>",
"task_status": "<string>",
"created_at": 123,
"updated_at": 123
}
}在你已经识别出源视频中的人脸后，使用此端点创建一个高级对口型任务。
调用前准备
- 先使用 Lip-Sync 获取
session_id和可用的face_id值 - 构建一个或多个
face_choose条目，将每张人脸映射到对应的音频片段 - 确保时间相关字段描述了音频应如何在视频中对齐
任务流程
先识别人脸
对源视频运行 Lip-Sync，并保留返回的
session_id 以及目标 face_id 值。完整参数参考请参见 Kling 官方文档。
授权
Bearer token authentication. Use your CometAPI key.
请求体
application/json
⌘I
Create an advanced Kling lip-sync task
curl --request POST \
--url https://api.cometapi.com/kling/v1/videos/advanced-lip-sync \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"session_id": "806556222048190514",
"face_choose": [
{
"face_id": "0",
"sound_file": "https://cdn1.suno.ai/e5c97078-3260-4354-a3a6-1d7249262a48.mp3",
"sound_start_time": "1200",
"sound_end_time": "5000",
"sound_insert_time": "0"
}
]
}
'{
"code": 123,
"message": "<string>",
"data": {
"task_id": "<string>",
"task_status": "<string>",
"created_at": 123,
"updated_at": 123
}
}