Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

WaveSpeed logo

SkyReels V3

SkyReels V3 creates talking-head videos from a portrait and recorded audio, with lip movements and facial expressions that follow the speech.

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.

SkyReels V3

SkyReels V3 turns a portrait and an audio recording into a speaking avatar video. The image establishes the presenter's appearance, while the recording drives the lip movements. Facial animation adds expression throughout the spoken delivery.

A text description can also guide the avatar's behavior, emotion, and camera style. This gives a recorded message a visual performance shaped around its tone, such as a composed presenter for an explanation or a cheerful speaker for an announcement.

What it's good for

Course creators can use it for instructor introductions and spoken lesson summaries. Presentation teams can turn recorded explanations into presenter-led segments, and marketing teams can develop spokesperson messages around a chosen portrait.

For localized content, pairing the same portrait with recordings in different languages provides a shared visual identity across versions. Each recording supplies the speech for its corresponding avatar performance.

Model ID

wavespeed-ai/skyreels-v3

Output Type

Video

Pricing

From $0.03 / input second

Provider

WaveSpeed

Hosting

Passthru

SkyReels V3

SkyReels V3 turns a portrait and an audio recording into a speaking avatar video. The image establishes the presenter's appearance, while the recording drives the lip movements. Facial animation adds expression throughout the spoken delivery.

A text description can also guide the avatar's behavior, emotion, and camera style. This gives a recorded message a visual performance shaped around its tone, such as a composed presenter for an explanation or a cheerful speaker for an announcement.

What it's good for

Course creators can use it for instructor introductions and spoken lesson summaries. Presentation teams can turn recorded explanations into presenter-led segments, and marketing teams can develop spokesperson messages around a chosen portrait.

For localized content, pairing the same portrait with recordings in different languages provides a shared visual identity across versions. Each recording supplies the speech for its corresponding avatar performance.