prunaai/p-video-avatar:c900d416 | Run with an API on Replicate

You're looking at a specific version of this model. Jump to the model overview.

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field	Type	Default value	Description
image	string		Input image (first frame). Supports jpg, jpeg, png, webp.
audio	string		Optional uploaded audio to drive lip-sync and duration. When set, it takes precedence over `script`; `voice`, `script`, and `speech_speed` are not used for the audio track.
script	string		Spoken text when no audio file is uploaded; ignored when `audio` is provided. Named `voice` values are synthesized with Kokoro. `voice` Auto uses Fish Audio S2 Pro–style synthesis (image-informed style) when Fish S2 is configured on this deployment.
voice	None	Auto	Voice for script-based speech when no `audio` is uploaded. Named options use Kokoro TTS. Auto uses Fish-styled speech when Fish S2 is configured; otherwise Auto is unavailable at runtime.
speech_speed	number	0.9 Min: 0.5 Max: 2	Tempo multiplier (0.5–2.0) for script-based speech. Applied inside Kokoro for named voices; for Auto (Fish S2), tempo is adjusted after synthesis.
prompt	string		Optional text prompt for additional guidance.
resolution	None	720p	Resolution of the video.
draft	boolean	False	Draft mode. Generates a lower-quality preview of the video.
disable_safety_filter	boolean	True	Disable safety filter for prompts and input image. When disabled, prompts are not checked for unsafe content before generation.
seed	integer		Random seed. Set for reproducible generation.
no_op	boolean	False	Health check mode — returns status without inference.

The shape of the response you’ll get when you run this model with an API.

Schema

{'format': 'uri', 'title': 'Output', 'type': 'string'}