创建对口型任务
Last updated: Nov 4, 2026
POST
基于人脸识别结果为指定人脸配音，参数对齐 原厂文档。
使用 TE 北京地域 API Key 鉴权。模型能力、调用约定见 Kling 接口概览。
BearerAuthheader
AuthorizationBearer <token>TE 北京地域 API Key，填写后自动添加 Bearer 前缀。
application/json- body
session_id*string人脸识别返回的 session_id
face_choose*array<>[{face_id, sound_file, sound_insert_time, sound_start_time, sound_end_time, sound_volume, original_audio_volume}]
external_task_id?string自定义任务 ID
callback_url?string回调地址
成功；具体状态及结果见响应字段。
application/json- response
taskId?stringcurl -X POST 'https://vod.bj.baidubce.com/v3/aigc/kl/videos/advanced-lip-sync' \ -H 'Content-Type: application/json' \ -d '{ "session_id": "<session_id>", "face_choose": [ { "face_id": "0", "sound_file": "https://example.com/speech.mp3", "sound_insert_time": 1000, "sound_start_time": 0, "sound_end_time": 3000, "sound_volume": 2, "original_audio_volume": 2 } ], "external_task_id": "", "callback_url": ""}'Example Response200
{ "taskId": "tsk-xxxxxxxxxxxxxxxx"}