Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

ByteDance logo

OmniHuman 1.5 Avatar

OmniHuman 1.5 Avatar animates portraits from voice recordings, combining lip sync with subtle eye movements and facial expressions informed by the audio.

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

OfferingPrice (USD)
native$0.16
  • Round billed duration up to a whole second before calculating the charge.
  • native: minimum billed duration 1s.

OmniHuman 1.5 Avatar

OmniHuman 1.5 Avatar generates an animated speaking character from a portrait and an audio recording. The portrait provides the visual identity, while the voice guides lip movement and emotional expression. Its facial animation includes small changes around the eyes and subtle expressions that contribute to the performance.

Both photographic portraits and stylized illustrations are supported. This lets an established character design or presenter photograph become the subject of a voice-driven video, with expression shaped by the supplied recording.

What it's good for

It suits narration where facial delivery matters, such as a character telling a story or a digital presenter explaining a topic. Expressive animation can give a pictured speaker a visible response to the tone of the recording.

Education teams can build instructor-led segments from portrait artwork and recorded lessons. Creative teams can also develop speaking characters for narrative clips, using existing illustrations as the basis for an on-screen performance.

Model ID

bytedance/omnihuman-1.5

Output Type

Video

Pricing

$0.16 / input second

Provider

ByteDance

Hosting

Passthru

OmniHuman 1.5 Avatar

OmniHuman 1.5 Avatar generates an animated speaking character from a portrait and an audio recording. The portrait provides the visual identity, while the voice guides lip movement and emotional expression. Its facial animation includes small changes around the eyes and subtle expressions that contribute to the performance.

Both photographic portraits and stylized illustrations are supported. This lets an established character design or presenter photograph become the subject of a voice-driven video, with expression shaped by the supplied recording.

What it's good for

It suits narration where facial delivery matters, such as a character telling a story or a digital presenter explaining a topic. Expressive animation can give a pictured speaker a visible response to the tone of the recording.

Education teams can build instructor-led segments from portrait artwork and recorded lessons. Creative teams can also develop speaking characters for narrative clips, using existing illustrations as the basis for an on-screen performance.