Lip Sync API - BudgetPixel API

Image + audio → talking video. Animate the person, character or pet in an image so it speaks your audio, with lips, expression and body motion in sync. Each model has its own endpoint, POST /v1/lip-sync/{model}.

Models

3 models. Each name opens its API reference with every parameter.

Model	Maker	What it does
OmniHuman 2.0 `omni-human-2.0`	ByteDance	The newest OmniHuman: animates the person (or character/pet) in an image to speak the input audio, with synchronized lips, expression, body motion and camera movement you can direct with a prompt.
OmniHuman 1.5 `omni-human-1.5`	ByteDance	Animates the person (or character/pet) in an image to speak the input audio with synchronized lips, facial expression, and body motion.
P-Video Avatar `p-video-avatar`	Pruna AI	A talking avatar from one image and a speech clip.

How a request works

Send POST /v1/lip-sync/{model} with an image and an audio clip. The response returns a job id right away.
Poll GET /v1/lip-sync/{id} until status is succeeded. The response then holds the video in video_url.

Media inputs covers passing the image and audio.

Pricing

Each model is priced per second of the input audio, rounded up to whole seconds. GET /v1/models returns current prices, and POST /v1/cost quotes a request before you send it. You pay only for jobs that succeed; see Pricing & credits.