Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

WaveSpeed logo

MultiTalk

MultiTalk turns a photo and supplied audio into a talking video, combining synchronized mouth movement with facial expression and body gestures.

Image to video

Based on verified input duration.

OfferingPrice (USD)
Usage rate$0.03 / input second
  • Based on the audio input; billing steps apply in this order:
  • Round input duration up to a whole second.
  • Cap billed duration at 600 seconds.
  • Bill at least 3 seconds.
  • Round the total charge up to the next $0.01.

MultiTalk

MultiTalk animates a still image into a talking video using supplied audio. The image provides the people and their appearance, while the recording drives lip movement and performance timing. A text description can guide the scene, pose, and behavior.

The animation includes facial expression and body gestures, giving the spoken performance movement throughout the visible figure. It also supports conversational scenes with multiple people. This combination suits material in which the delivery of a line matters alongside the words being spoken.

What it's good for

MultiTalk can turn a presenter portrait and narration into an educational explainer, training segment, or spoken social post. Dialogue scenes provide another application, with people pictured together taking part in a conversation. For localized presenter content, a different spoken recording can drive the visible mouth movements, allowing the performance to follow the supplied speech.

Model ID

wavespeed-ai/multitalk

Output Type

Video

Pricing

$0.03 / input second

Provider

WaveSpeed

Hosting

Passthru

MultiTalk

MultiTalk animates a still image into a talking video using supplied audio. The image provides the people and their appearance, while the recording drives lip movement and performance timing. A text description can guide the scene, pose, and behavior.

The animation includes facial expression and body gestures, giving the spoken performance movement throughout the visible figure. It also supports conversational scenes with multiple people. This combination suits material in which the delivery of a line matters alongside the words being spoken.

What it's good for

MultiTalk can turn a presenter portrait and narration into an educational explainer, training segment, or spoken social post. Dialogue scenes provide another application, with people pictured together taking part in a conversation. For localized presenter content, a different spoken recording can drive the visible mouth movements, allowing the performance to follow the supplied speech.