Lip sync with OmniHuman 1.5
BytePlus OmniHuman 1.5 — animates the person (or character/pet) in an image to speak the input audio with synchronized lips, facial expression, and body motion. Priced per second of the input audio, rounded UP to whole seconds (135 credits/second — e.g. a 12.4s clip bills as 13s).
Asynchronous. Returns a job id (the video is not in this response). Poll GET /v1/lip-sync/{id} until status is succeeded — the video URL is in that response’s video_url.
Authorizations
API key as a bearer token: Authorization: Bearer bpx_live_xxx
Body
The speech/audio to lip-sync (mp3/wav, up to 60 seconds, max 5 MB). A public audio URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads.
The subject to animate — a human face/portrait, character, or pet. A public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. jpg/png/webp.
Output resolution (same price for both).
720, 1080 Optional text prompt to guide the animation style or actions.
Response
Job accepted.
Total price of this job (seconds x the model's per-second rate).
Opaque job id (mtn_...) — use it to poll status.
Billed duration — the reference video's length
Lifecycle state. succeeded/failed/timeout are terminal.
pending, starting, processing, completing, succeeded, failed, timeout