Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

WaveSpeed logo

WAN 2.2 Speech to Video

WAN 2.2 Speech to Video animates a still image with supplied speech, combining synchronized lip movement with facial expression and body motion.

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

OfferingPrice (USD)
480p$0.03
720p$0.06
  • Round billed duration up to a whole second before calculating the charge.
  • 480p: minimum billed duration 3s.
  • 720p: minimum billed duration 3s.

WAN 2.2 Speech to Video

WAN 2.2 Speech to Video creates a speaking-character video from a still image and an audio recording. The image establishes the visual subject, while the recording supplies the spoken performance. Generated lip movements follow the audio, accompanied by facial expressions and body movement.

Optional text guidance can shape the scene and the character's pose or behavior while preserving the connection to the speech. This combines an existing voice performance with visual direction, giving the character a way to act within the scene as the recording plays.

What it's good for

Presenter-led explainers and narrated training material are useful applications. A prepared character image and recorded narration can become an on-screen performance for a lesson or presentation.

For story development, the model can turn character artwork and dialogue recordings into performance studies. These clips help a production team consider how the voice delivery relates to expression and physical behavior during a spoken scene.

Model ID

wavespeed-ai/wan-2.2-speech-to-video

Output Type

Video

Pricing

From $0.03 / input second

Provider

WaveSpeed

Hosting

Protoface

WAN 2.2 Speech to Video

WAN 2.2 Speech to Video creates a speaking-character video from a still image and an audio recording. The image establishes the visual subject, while the recording supplies the spoken performance. Generated lip movements follow the audio, accompanied by facial expressions and body movement.

Optional text guidance can shape the scene and the character's pose or behavior while preserving the connection to the speech. This combines an existing voice performance with visual direction, giving the character a way to act within the scene as the recording plays.

What it's good for

Presenter-led explainers and narrated training material are useful applications. A prepared character image and recorded narration can become an on-screen performance for a lesson or presentation.

For story development, the model can turn character artwork and dialogue recordings into performance studies. These clips help a production team consider how the voice delivery relates to expression and physical behavior during a spoken scene.