Skip to main content
POST
Lip sync with OmniHuman 2.0

Authorizations

Authorization
string
header
required

API key as a bearer token: Authorization: Bearer bpx_live_xxx

Body

application/json
audio
string
required

The speech/audio to lip-sync (mp3, wav or ogg, up to 120 seconds, max 15 MB; under 4 seconds is billed as 4). A public audio URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads.

image
string
required

The subject to animate — a human face/portrait, character, or pet. 300-6000 px a side, aspect ratio between 2:5 and 5:2. A public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. jpg/png/webp.

prompt
string

Optional text prompt to direct the scene, gestures and camera movement (Chinese, English, Japanese, Korean, Spanish or Indonesian).

Response

Job accepted.

credits
integer

Total price of this job (seconds x the model's per-second rate).

id
string

Opaque job id (mtn_...) — use it to poll status.

message
string
model
string
seconds
integer

Billed duration — the reference video's length, rounded up.

status
enum<string>

Lifecycle state. succeeded/failed/timeout are terminal.

Available options:
pending,
starting,
processing,
completing,
succeeded,
failed,
timeout