Automate tasks with KlingAI

Actions

The action is what happens automatically, without you having to do anything else.

• 

  Generate Video from Image

  Creates a video that starts from an image (and optionally ends on another), guided by a text prompt, with the KlingAI model you choose (the list is read from Kling's docs, so it always shows the current models).

• 

  Generate Video from Multiple Images

  Creates a video from up to 4 reference images (characters, scenes, style) and a text prompt, with a KlingAI Omni model (the list is read from Kling's docs).

• 

  Generate Audio from Text

  Creates a sound (effects, ambience) from a text prompt. Duration between 3 and 10 seconds.

• 

  Generate Video from Text

  Creates a video from a text prompt with the KlingAI model you choose (the list is read from Kling's docs, so it always shows the current models).