> ## Documentation Index
> Fetch the complete documentation index at: https://docs.jiekou.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Kling V2.1 Master Text-to-Video

Kling V2.1 Text-to-Video is the latest-generation text-to-video model developed by the Kuaishou AI team. It can generate high-quality, cinematic short videos from input text with a single click. Compared with Kling 2.0, version 2.1 delivers major breakthroughs in motion fluidity, visual consistency, prompt understanding, and more.

<Tip>
  This is an **asynchronous** API and only returns the task\_id of the asynchronous task. You should use this task\_id to request the [Query Task Result API](/en/docs/models/reference-get-async-task-result) to retrieve the video generation result.
</Tip>

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum value: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="prompt" type="string" required={true}>
  The positive text prompt that guides generation. Maximum length: 2500 characters.
</ParamField>

<ParamField body="duration" type="string" default="5">
  The duration of the generated video (in seconds).

  Available values: `5`, `10`
</ParamField>

<ParamField body="aspect_ratio" type="string" default="16:9">
  The aspect ratio of the output video.

  Available values: `16:9`, `9:16`, `1:1`
</ParamField>

<ParamField body="guidance_scale" type="number" default={0.5}>
  The guidance strength parameter, which controls how closely the generated content matches the prompt.

  Value range: 0 to 1<br />
  Step: 0.1
</ParamField>

<ParamField body="negative_prompt" type="string">
  The negative prompt, used to avoid undesired content. Maximum length: 2500 characters.
</ParamField>

## Response

<ResponseField name="task_id" type="string" required={true}>
  The task\_id of the asynchronous task. You should use this task\_id to request the [Query Task Result API](/en/docs/models/reference-get-async-task-result) to obtain the generation result
</ResponseField>