> ## 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.

# Wan 2.5 Preview Text-to-Video

The Wan 2.5 Preview text-to-video model supports generating high-quality video content from text descriptions, and can generate videos of 5 or 10 seconds. New audio capabilities: supports automatic voiceover, and also allows custom audio files.

<Tip>
  This is an **asynchronous** API and will only return the asynchronous task's task\_id. You should use this task\_id to request the [Get 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="input" type="object" required={true}>
  Basic input information, such as prompts.

  <Expandable title="Field Descriptions" defaultOpen={true}>
    <ParamField body="prompt" type="string" required={true}>
      Text positive prompt. Chinese and English are supported, up to 2000 characters. Any excess will be automatically truncated.

      Example value: A kitten running under the moonlight.
    </ParamField>

    <ParamField body="negative_prompt" type="string" required={false}>
      Negative prompt, used to describe content to avoid when generating the video, enabling avoidance or restriction of the image.

      Chinese and English are supported, up to 500 characters. Any excess will be automatically truncated.

      Example value: low resolution, errors, worst quality, low quality, incomplete, extra fingers, poor proportions, etc.
    </ParamField>

    <ParamField body="audio_url" type="string" required={false}>
      The URL of a custom audio file used for video generation. For usage details, see the audio settings instructions.

      Audio requirements:

      * Format: wav, mp3.
      * Duration: 3–30 seconds.
      * File size: no more than 15 MB.

      Handling for overlong audio: If the audio duration exceeds the target video duration (for example, 5 seconds or 10 seconds), only the first 5 seconds or first 10 seconds will be retained, and the rest will be automatically discarded; if the audio duration is shorter than the video duration, the remaining part will be a silent video. For example, if the audio is 3 seconds and the video is 5 seconds, the first 3 seconds of the output video will have sound, and the last 2 seconds will be silent.
    </ParamField>
  </Expandable>
</ParamField>

<ParamField body="parameters" type="object" required={false}>
  Video processing parameters.

  <Expandable title="Field Descriptions" defaultOpen={true}>
    <ParamField body="size" type="string" required={false}>
      Supports 480P, 720P, and 1080P resolutions. Default value: `1920*1080` (i.e., 1080P).
      The `size` parameter is used to specify the resolution of the video output, in the format width\*height. The specific supported values for each resolution tier are as follows:

      **480P tier**: Available resolutions

      * `832*480`: 16:9
      * `480*832`: 9:16
      * `624*624`: 1:1

      **720P tier**: Available resolutions

      * `1280*720`: 16:9
      * `720*1280`: 9:16
      * `960*960`: 1:1
      * `1088*832`: 4:3
      * `832*1088`: 3:4

      **1080P tier**: Available resolutions

      * `1920*1080`: 16:9
      * `1080*1920`: 9:16
      * `1440*1440`: 1:1
      * `1632*1248`: 4:3
      * `1248*1632`: 3:4

      <Warning>
        **Common misconception about the size parameter**: You must provide a specific resolution (such as `1280*720`), not an aspect ratio (such as `1:1`) or a tier name (such as `480P` or `720P`).
      </Warning>
    </ParamField>

    <ParamField body="duration" type="integer" required={false}>
      Duration of the output video. Available values: `5` seconds, `10` seconds.

      Default value: `5`.
    </ParamField>

    <ParamField body="prompt_extend" type="bool" required={false}>
      Whether to enable intelligent prompt rewriting. When enabled, a large model will be used to automatically rewrite the input prompt. This improves generation results for shorter prompts, but increases processing time.

      * `true`: Default, enables intelligent rewriting
      * `false`: No rewriting
    </ParamField>

    <ParamField body="audio" type="boolean" required={false}>
      Whether to add audio.

      Parameter priority: audio\_url > audio. Effective only when audio\_url is empty.

      * `true`: Default, automatically adds voiceover to the video
      * `false`: Does not add audio; the output is a silent video

      Example value: true
    </ParamField>

    <ParamField body="seed" type="integer" required={false}>
      Random seed, used to control the randomness of model-generated content. Value range: \[0, 2147483647].

      If not provided, the system automatically generates a random seed. If you want the generated results to be relatively stable and consistent, you can specify the same seed value.
    </ParamField>
  </Expandable>
</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 [Get Task Result API](/en/docs/models/reference-get-async-task-result) to obtain the generation result.
</ResponseField>