Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

Kuaishou logo

Kling V1 AI Avatar Standard

Kling V1 AI Avatar Standard turns a portrait and recorded or synthetic speech into talking-head video, coordinating lip movement with blinks and head motion.

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

OfferingPrice (USD)
native$0.05
  • Round billed duration up to a whole second before calculating the charge.
  • native: minimum billed duration 3s.

Kling V1 AI Avatar Standard

Kling V1 AI Avatar Standard creates a speaking avatar from a portrait and an audio track. The image supplies the presenter's likeness, while the audio determines the speech. Both recorded voices and text-to-speech recordings can provide the narration.

The animation matches mouth movement to speech sounds and adds blinking and head movement. Identity preservation keeps the depicted speaker recognizable as the portrait moves. Optional text guidance can influence the framing or visual style of the presentation.

What it's good for

Training teams can turn narrated procedures into presenter-led segments, using an established portrait across related lessons. A support avatar can explain an account process or introduce a help topic with a visible speaker delivering the supplied recording.

It also fits product-demo introductions and educational explainers. Teams working with synthetic narration can prepare the voice track separately, then combine it with a presenter image to produce the talking-head footage.

Model ID

kuaishou/kling-v1-ai-avatar-standard

Output Type

Video

Pricing

$0.05 / input second

Provider

Kuaishou

Hosting

Passthru

Kling V1 AI Avatar Standard

Kling V1 AI Avatar Standard creates a speaking avatar from a portrait and an audio track. The image supplies the presenter's likeness, while the audio determines the speech. Both recorded voices and text-to-speech recordings can provide the narration.

The animation matches mouth movement to speech sounds and adds blinking and head movement. Identity preservation keeps the depicted speaker recognizable as the portrait moves. Optional text guidance can influence the framing or visual style of the presentation.

What it's good for

Training teams can turn narrated procedures into presenter-led segments, using an established portrait across related lessons. A support avatar can explain an account process or introduce a help topic with a visible speaker delivering the supplied recording.

It also fits product-demo introductions and educational explainers. Teams working with synthetic narration can prepare the voice track separately, then combine it with a presenter image to produce the talking-head footage.