Video Generation

Available video models

Model slug	Display name	Tasks
`seedance-2.0`	Seedance 2.0	text-to-video, image-to-video
`kling-v3.0-std`	Kling 3.0	text-to-video, image-to-video
`veo3.1`	Veo 3.1	text-to-video
`sora-2`	Sora 2	text-to-video, image-to-video
`wan-2.1`	Wan 2.1	text-to-video, image-to-video
`hailuo-v2`	Hailuo V2	text-to-video, image-to-video
`luma-ray-2`	Luma Ray 2	text-to-video, image-to-video

For the full list, see the model catalog.

Text to video

Generate a video from a text prompt.

cURL

curl -X POST https://aircube.ai/api/v3/seedance-2.0/text-to-video \
  -H "Authorization: Bearer $AIRCUBE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "a drone shot flying over a mountain lake at sunrise, cinematic",
    "duration": "5",
    "aspect_ratio": "16:9"
  }'

Python

import os
import time
import requests

API_KEY = os.environ["AIRCUBE_API_KEY"]
BASE_URL = "https://aircube.ai/api/v3"
HEADERS = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json",
}

# Submit
response = requests.post(
    f"{BASE_URL}/seedance-2.0/text-to-video",
    headers=HEADERS,
    json={
        "prompt": "a drone shot flying over a mountain lake at sunrise, cinematic",
        "duration": "5",
        "aspect_ratio": "16:9",
    },
)
generation_id = response.json()["data"]["id"]

# Poll (use longer interval for video)
while True:
    result = requests.get(f"{BASE_URL}/status/{generation_id}", headers=HEADERS).json()
    if result["data"]["status"] == "completed":
        print(result["data"]["output_url"])
        break
    elif result["data"]["status"] == "failed":
        print("Failed")
        break
    time.sleep(5)

JavaScript

const API_KEY = process.env.AIRCUBE_API_KEY;
const BASE_URL = "https://aircube.ai/api/v3";

const submitRes = await fetch(`${BASE_URL}/seedance-2.0/text-to-video`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "a drone shot flying over a mountain lake at sunrise, cinematic",
    duration: "5",
    aspect_ratio: "16:9",
  }),
});
const { data } = await submitRes.json();

while (true) {
  const pollRes = await fetch(`${BASE_URL}/status/${data.id}`, {
    headers: { Authorization: `Bearer ${API_KEY}` },
  });
  const result = await pollRes.json();
  if (result.data.status === "completed") {
    console.log(result.data.output_url);
    break;
  } else if (result.data.status === "failed") {
    throw new Error("Failed");
  }
  await new Promise((r) => setTimeout(r, 5000));
}

Image to video

Animate a still image into a video. Provide the source image via the image parameter.

cURL

curl -X POST https://aircube.ai/api/v3/kling-v3.0-std/image-to-video \
  -H "Authorization: Bearer $AIRCUBE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "the character turns and smiles at the camera",
    "image": "https://example.com/character.jpg",
    "duration": "5"
  }'

Python

response = requests.post(
    f"{BASE_URL}/kling-v3.0-std/image-to-video",
    headers=HEADERS,
    json={
        "prompt": "the character turns and smiles at the camera",
        "image": "https://example.com/character.jpg",
        "duration": "5",
    },
)
generation_id = response.json()["data"]["id"]

while True:
    result = requests.get(f"{BASE_URL}/status/{generation_id}", headers=HEADERS).json()
    if result["data"]["status"] in ("completed", "failed"):
        print(result["data"])
        break
    time.sleep(5)

JavaScript

const submitRes = await fetch(`${BASE_URL}/kling-v3.0-std/image-to-video`, {
  method: "POST",
  headers: {
    Authorization: `Bearer ${API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "the character turns and smiles at the camera",
    image: "https://example.com/character.jpg",
    duration: "5",
  }),
});

Parameters

duration

Controls the length of the generated video in seconds. Pass it as a string:

{ "duration": "5" }

Common values: "3", "5", "10". Longer videos cost more credits. Available durations depend on the model.

aspect_ratio

Controls the output aspect ratio. Common values:

Value	Use case
`16:9`	Landscape — standard widescreen
`9:16`	Portrait — vertical/mobile video
`1:1`	Square — social media

resolution

Specify an exact output resolution:

{ "resolution": "1280x720" }

image

A URL to a source image for image-to-video tasks. The image is downloaded and stored automatically:

{ "image": "https://example.com/source.jpg" }

Tips

Descriptive prompts produce better results. Include camera movement, lighting, and action descriptions.
Image-to-video tends to produce more consistent results than text-to-video since the model has a visual reference.
Poll every 5 seconds for video — generation typically takes 30 seconds to several minutes depending on the model and duration.
Download output promptly — signed output URLs expire after 7 days.

Video Generation

On this page