# Kling O3 (https://docs.fuser.studio/docs/nodes/video/kling-o3)

_Provided by [Fal](https://fal.ai) — [Learn More](https://fal.ai/models/fal-ai/kling-video/o3/standard/text-to-video)._

Model page: https://fuser.studio/models/kling-o3

## Inputs [#inputs]

- **Prompt** (`textarea`) — Describe the video; reference images as @Image1, @Image2, and so on.

- **Model** (`dropdown`) — Choose Standard or Pro output quality.

   Optional: `true` • Default: `standard` • Accepts: `Standard`, `Pro`

- **Start Image** (`image`) — First frame. A start image selects image-to-video unless reference images are also supplied.

   Optional: `true`

- **End Image** (`image`) — Optional ending frame; requires a start image.

   Optional: `true`

- **Reference Images** (`image`) _(accepts multiple)_ — Images that guide subject, scene, or style consistency. Cite each image in the prompt.

   Optional: `true`

- **Duration** (`slider`) — Video duration in seconds, from 3 to 15.

   Optional: `true` • Default: `5` • Minimum: `3` • Maximum: `15`

- **Aspect Ratio** (`dropdown`) — Aspect ratio of the video.

   Optional: `true` • Default: `16:9` • Accepts: `16:9`, `9:16`, `1:1`

- **Generate Audio** (`toggle`) — Generate native synchronized audio.

   Optional: `true` • Default: `false`

## Outputs [#outputs]

- **Generated Video** (`video`) — The generated video.