P Video Avatar

P Video Avatar creates a talking avatar from an image and audio, using the recording to drive speech and lip sync with optional guidance for movement and expression.

Price per input second. Round the total charge up to the next $0.01.

Offering	Price (USD)
720p	$0.025
1080p	$0.045

Round billed duration up to a whole second before calculating the charge.
720p: minimum billed duration 1s.
1080p: minimum billed duration 1s.

P Video Avatar

P Video Avatar turns a reference image and an audio recording into an avatar performance. The image defines the visible character, while the recording drives speech and lip sync. This connects a chosen portrait or character design to the delivery of an existing voice performance.

Optional text guidance shapes motion, expression, and performance style. It can also direct body movement and framing behavior, giving the avatar a visual treatment suited to the spoken material. The supplied audio remains the basis for the performance's timing and delivery.

What it's good for

The model suits narrated character introductions and talking-portrait presentations. A designer can pair character artwork with recorded dialogue to explore how a scene plays, while a presentation team can develop a virtual presenter around an established face and voice.

It also supports avatar-led social content and storytelling prototypes. These applications let teams assess a character's on-screen delivery using the artwork and audio prepared for the project.

Model ID

pruna-ai/p-video-avatar

Output Type

Video

Pricing

From $0.025 / input second

Provider

Pruna

Hosting

Passthru

P Video Avatar

What it's good for

It also supports avatar-led social content and storytelling prototypes. These applications let teams assess a character's on-screen delivery using the artwork and audio prepared for the project.