Novita AI Wan 2.5 Preview Text to Video API

Wan 2.5 Preview Text to Video

curl --request POST \
  --url https://api.novita.ai/v3/async/wan-2.5-t2v-preview \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "input": {
    "prompt": "<string>",
    "negative_prompt": "<string>",
    "audio_url": "<string>"
  },
  "parameters": {
    "size": "<string>",
    "duration": 123,
    "prompt_extend": true,
    "audio": true,
    "seed": 123
  }
}
'

{
  "task_id": "<string>"
}

POST

https://api.novita.ai

async

wan-2.5-t2v-preview

Wan 2.5 Preview Text to Video

curl --request POST \
  --url https://api.novita.ai/v3/async/wan-2.5-t2v-preview \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "input": {
    "prompt": "<string>",
    "negative_prompt": "<string>",
    "audio_url": "<string>"
  },
  "parameters": {
    "size": "<string>",
    "duration": 123,
    "prompt_extend": true,
    "audio": true,
    "seed": 123
  }
}
'

{
  "task_id": "<string>"
}

Wan 2.5 Preview Text-to-Video model can generate high-quality video content based on text descriptions, and can produce videos with durations of 5 seconds and 10 seconds. New audio capabilities: supports automatic dubbing, or you can provide a custom audio file.

This is an asynchronous API; only the task_id will be returned. You should use the task_id to request the Task Result API to retrieve the video generation results.

Request Headers

Content-Type

string

required

Supports: application/json

Authorization

string

required

Bearer authentication format, for example: Bearer {{API Key}}.

Request Body

input

object

required

Basic input information, such as prompts.

Hide properties

prompt

string

required

Text prompt. Supports both English and Chinese, with a maximum length of 2000 characters, and any excess will be automatically truncated.Example value: A small cat running under the moonlight.

negative_prompt

string

Negative prompt, used to describe content that should be avoided in the video, allowing for restrictions on the video content.Supports both English and Chinese, with a maximum length of 500 characters. Any excess will be automatically truncated.Example value: Low resolution, errors, worst quality, low quality, incomplete, extra fingers, disproportionate, etc.

audio_url

string

URL of the audio file that the model will use to generate the video. See audio settings for usage instructions.Audio restrictions:

Format: wav, mp3.
Duration: 3-30s.
File size: No more than 15MB.

Overflow handling: If the audio length exceeds the duration value (5 seconds or 10 seconds), the first 5 seconds or 10 seconds will be automatically truncated, and the rest will be discarded. If the audio length is shorter than the video duration, the part beyond the audio length will be silent video. For example, if the audio is 3 seconds and the video duration is 5 seconds, the output video will have sound for the first 3 seconds and be silent for the last 2 seconds.

parameters

object

Video processing parameters.

Hide properties

size

string

Supports resolutions for 480P, 720P, and 1080P. Default value: 1920*1080 (1080P). Used to specify the video resolution in the format of width*height. The supported resolutions for different models are as follows:480P tier: Available video resolutions and their corresponding aspect ratios are:

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

720P tier: Available video resolutions and their corresponding aspect ratios are:

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

1080P tier: Available video resolutions and their corresponding aspect ratios are:

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

Common misconceptions about the size parameter: The size must be set to the specific values of the target resolution (e.g., 1280*720), not the aspect ratio (e.g., 1:1) or resolution tier name (e.g., 480P or 720P).

duration

integer

Specifies the duration of the generated video. Supported values: 5 or 10 seconds.Default value: 5.

prompt_extend

bool

Whether to enable intelligent prompt rewriting. When enabled, a large model is used to intelligently rewrite the input prompt. This significantly improves the generation effect for shorter prompts but increases processing time.

true: Default value, enable intelligent rewriting.
false: Do not enable intelligent rewriting.

audio

boolean

Used to control whether to add audio.Parameter priority: audio_url > audio, only takes effect when audio_url is empty.

true: Default value, automatically add audio to the video.
false: Do not add audio, output silent video.

Example value: true.

seed

integer

Random seed, used to control the randomness of the model’s generated content. The value range is [0, 2147483647].If not provided, the algorithm automatically generates a random number as the seed. To maintain relatively stable generated content, you can use the same seed parameter value.

Response

task_id

string

required

Use the task_id to request the Task Result API to retrieve the generated outputs.

Wan 2.2 Image to Video Wan 2.5 Preview Image to Video

⌘I

Basic

Model APIs

GPUs

Wan 2.5 Preview Text to Video

Request Headers

Request Body

Response

Basic

Model APIs

GPUs

​Request Headers

​Request Body

​Response

Request Headers

Request Body

Response