GlobalAiOpc
DigitalHuman - Create Task
Submit a digital human lip-sync video task
DigitalHuman Create Task
Submit a digital human lip-sync video task. The API accepts an audio URL and a video URL, then generates a digital human video with mouth movements matched to the audio.
认证
获取 KeyAll requests must include a Bearer token in the request header:
cURL
Authorization: Bearer {{key}}
Base URL
https://zcbservice.aizfw.cn/kyyReactApiServerbaseUrl is the shared prefix for all public APIs. The api field in the current page frontmatter shows the full endpoint. Use this baseUrl as the common prefix when reading or composing request paths.Request Parameters
modelbodystringrequiredModel name. Defaults to
kyy_digitalHuman.audioUrlbodystringrequiredAudio URL. The resource must be a network URL, not a local file path. Do not include Chinese characters in the URL.
Supported formats:
mp4, mp3, wav, m4a, aar.videoUrlbodystringrequiredVideo URL. The resource must be a network URL, not a local file path. Do not include Chinese characters in the URL.
modelVersionbodyintegerModel version.
1: Clearer teeth, better performance for close-up face scenarios2: Better lip-sync matching and faster articulation; recommended as the default choice
sideFacebodyintegerSide-face optimization parameter. Pass
1 if the video contains a very strong side-face angle.For normal cases, omit this parameter or pass
0. Omitting it usually gives the best result.tiltedFacebodyintegerTilted-face optimization parameter. Pass
1 if the person is facing forward but the head is tilted and the mouth is slanted.For normal cases, omit this parameter or pass
0. Omitting it usually gives the best result.Response Parameters
idstringTask ID, used to query the task status later.
objectstringObject type, fixed as
video.createdintegerTask creation timestamp.
modelstringModel name used by the task.
statusstringTask status. It is usually
queued after creation.errorstringError message, returned when the task fails.
