Digital Human Video API
POSThttps://api.acedata.cloud/digital-human/videos

Digital Human video generation API — turn a portrait plus audio or text into a talking-head video.

Request Headers

authorizationstring
Bearer token

Request Body

textstring
Spoken text -> TTS (requires voice_id).
asyncboolean
Please select
speednumber
Audio tempo multiplier.
stepsinteger
Diffusion steps (LatentSync).
enginestring
[Deprecated] Accepted for backward compatibility but no longer changes the output or the price — every request is billed at the unified rate.
Please select
guidancenumber
Lip-sync strength (LatentSync). Lower loosens sync.
seam_fixboolean
Apply the mouth-seam reduction blend.
Please select
voice_idstring
A cloned voice from POST /digital-human/voices.
audio_urlstring
Public URL of the driving audio (.wav/.mp3/.m4a). OR supply text(+voice_id).
image_urlstring
Public URL of a source face photo (photo-driven path). Supply either video_url or image_url.
video_urlstring
Public URL of the source face video (preferred). Supply either video_url or image_url.
resolutionstring
[Deprecated] Output is always rendered at 720p.
Please select
callback_urlstring
Webhook; if set (or async=true) returns task_id immediately.

Response

Integration guide

Shell

Python

JavaScript

Java

Go

PHP

Kind reminder: For streaming requests, the above code may not be fully applicable. Please refer to the integration documentation for changes.

Digital Human
Allow Use General Balance

When 'Allow General Balance' is enabled, the general balance is used automatically if an app's balance is insufficient.