Lip sync with P-Video Avatar
P-Video Avatar — a talking avatar from one image and a speech clip. Priced per second of the input audio, rounded UP to whole seconds, by output resolution: 40 credits/second at 720p, 60 credits/second at 1080p (e.g. a 12.4s clip at 1080p bills as 13s x 60).
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 30 seconds, max 5 MB). A public audio URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads.
The avatar image (a person facing the camera works best). A public image URL, a data URI, raw base64, or an uploaded-file URL from POST /v1/uploads. jpg/png/webp.
Output resolution — sets the per-second price (720p = 40, 1080p = 60 credits/second).
720p, 1080p Optional visual prompt describing how the person should appear or behave while speaking.
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