All Models

Kuaishou logo

Kling V2.6 Pro

Kling V2.6 Pro generates video with optional sound from text and animates pictured characters using movement transferred from reference footage.

Video Motion Control

Based on verified input duration.

OfferingPrice (USD)
All listed options$0.112 / input second
  • Character Orientation: image, video (same price).
  • Keep Original Sound: Off, On (same price).
  • Based on the video input; billing steps apply in this order:
  • Round input duration up to a whole second.
  • Cap billed duration at 30 seconds.
  • Bill at least 3 seconds.
  • Round the total charge up to the next $0.01.

Text to video

Price per run for each listed option.

OfferingPrice (USD)
Duration: 5s · Sound: Off$0.35 / run
Duration: 5s · Sound: On$0.70 / run
Duration: 10s · Sound: Off$0.70 / run
Duration: 10s · Sound: On$1.40 / run

Kling V2.6 Pro

Kling V2.6 Pro supports text-to-video generation with optional audio, alongside reference-based motion transfer. Written scenes can guide character action and camera movement, with voices, ambience and sound effects generated together with the visuals.

Motion transfer starts from a character image and a performance video. The image supplies the subject’s appearance, while the clip supplies body movement, including posture and limb positions. Text can refine the scene’s styling or lighting, and the original performance audio can be retained.

What it's good for

Text-led generation suits story concepts and advertising drafts where action and sound need to be reviewed together. A product explainer concept, for example, can include spoken description alongside the on-screen activity.

Reference-driven animation suits choreography studies and mascot performances built around recorded movement. These creation methods serve different production needs: scene invention from a written brief, and character animation grounded in a specific physical performance.

Model ID

kuaishou/kling-v2.6-pro

Output Type

Video

Pricing

Varies by inputs · see pricing table

Provider

Kuaishou

Hosting

Passthru

Kling V2.6 Pro

Kling V2.6 Pro supports text-to-video generation with optional audio, alongside reference-based motion transfer. Written scenes can guide character action and camera movement, with voices, ambience and sound effects generated together with the visuals.

Motion transfer starts from a character image and a performance video. The image supplies the subject’s appearance, while the clip supplies body movement, including posture and limb positions. Text can refine the scene’s styling or lighting, and the original performance audio can be retained.

What it's good for

Text-led generation suits story concepts and advertising drafts where action and sound need to be reviewed together. A product explainer concept, for example, can include spoken description alongside the on-screen activity.

Reference-driven animation suits choreography studies and mascot performances built around recorded movement. These creation methods serve different production needs: scene invention from a written brief, and character animation grounded in a specific physical performance.