Quickstart

End-to-end examples for image, video, and audio generation with the AirCube API.

Three complete examples — text-to-image, image-to-video, and text-to-speech — each showing the full submit-and-poll workflow.

Prerequisites

An AirCube account with credits (sign up)
An API key in the AIRCUBE_API_KEY environment variable (create one)

Step 0: Discover models

List all available models to find the slug and supported tasks:

curl https://aircube.ai/api/v3/models \
  -H "Authorization: Bearer $AIRCUBE_API_KEY"

Each entry returns slug, tasks, and price_from_usd. Use slug + tasks[n] to build your submit URL.

Example 1: Text to image

Generate an image with Seedream 5.0 Pro (seedream-v5.0-pro).

cURL

# Submit
curl -X POST https://aircube.ai/api/v3/seedream-v5.0-pro/text-to-image \
  -H "Authorization: Bearer $AIRCUBE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "a photorealistic glass cube refracting light, on a marble surface",
    "aspect_ratio": "1:1",
    "resolution": "2k"
  }'

# Poll (replace ID with the value from the response)
curl https://aircube.ai/api/v3/status/YOUR_GENERATION_ID \
  -H "Authorization: Bearer $AIRCUBE_API_KEY"

Python

import os, time, requests

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

# Submit
res = requests.post(f"{BASE}/seedream-v5.0-pro/text-to-image", headers=HEADERS, json={
    "prompt": "a photorealistic glass cube refracting light, on a marble surface",
    "aspect_ratio": "1:1",
    "resolution": "2k",
})
gen_id = res.json()["data"]["id"]
print(f"Submitted: {gen_id}")

# Poll
while True:
    result = requests.get(f"{BASE}/status/{gen_id}", headers=HEADERS).json()
    status = result["data"]["status"]
    print(f"Status: {status}")
    if status == "completed":
        print(f"Output: {result['data']['output_url']}")
        break
    elif status == "failed":
        print("Generation failed")
        break
    time.sleep(3)

JavaScript

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

// Submit
const submitRes = await fetch(`${BASE}/seedream-v5.0-pro/text-to-image`, {
  method: "POST",
  headers: { Authorization: `Bearer ${API_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({
    prompt: "a photorealistic glass cube refracting light, on a marble surface",
    aspect_ratio: "1:1",
    resolution: "2k",
  }),
});
const genId = (await submitRes.json()).data.id;
console.log(`Submitted: ${genId}`);

// Poll
while (true) {
  const poll = await fetch(`${BASE}/status/${genId}`, {
    headers: { Authorization: `Bearer ${API_KEY}` },
  });
  const { data } = await poll.json();
  console.log(`Status: ${data.status}`);
  if (data.status === "completed") { console.log(`Output: ${data.output_url}`); break; }
  if (data.status === "failed") throw new Error("Generation failed");
  await new Promise((r) => setTimeout(r, 3000));
}

Example 2: Image to video

Animate a still image with Seedance 2.0 (seedance-2.0).

cURL

curl -X POST https://aircube.ai/api/v3/seedance-2.0/image-to-video \
  -H "Authorization: Bearer $AIRCUBE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "the cube slowly rotates and light refracts through it",
    "image": "https://example.com/your-image.jpg",
    "duration": "5",
    "resolution": "720p"
  }'

Python

res = requests.post(f"{BASE}/seedance-2.0/image-to-video", headers=HEADERS, json={
    "prompt": "the cube slowly rotates and light refracts through it",
    "image": "https://example.com/your-image.jpg",
    "duration": "5",
    "resolution": "720p",
})
gen_id = res.json()["data"]["id"]

while True:
    result = requests.get(f"{BASE}/status/{gen_id}", headers=HEADERS).json()
    if result["data"]["status"] == "completed":
        print(f"Video: {result['data']['output_url']}")
        break
    elif result["data"]["status"] == "failed":
        print("Failed"); break
    time.sleep(5)  # Videos take longer

JavaScript

const submitRes = await fetch(`${BASE}/seedance-2.0/image-to-video`, {
  method: "POST",
  headers: { Authorization: `Bearer ${API_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({
    prompt: "the cube slowly rotates and light refracts through it",
    image: "https://example.com/your-image.jpg",
    duration: "5",
    resolution: "720p",
  }),
});
const { data } = await submitRes.json();

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

Example 3: Text to speech

Synthesize speech with Qwen3 TTS (qwen3-tts).

cURL

curl -X POST https://aircube.ai/api/v3/qwen3-tts/text-to-speech \
  -H "Authorization: Bearer $AIRCUBE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Welcome to AirCube. The unified API for AI generation."}'

Python

res = requests.post(f"{BASE}/qwen3-tts/text-to-speech", headers=HEADERS, json={
    "prompt": "Welcome to AirCube. The unified API for AI generation.",
})
gen_id = res.json()["data"]["id"]

while True:
    result = requests.get(f"{BASE}/status/{gen_id}", headers=HEADERS).json()
    if result["data"]["status"] == "completed":
        print(f"Audio: {result['data']['output_url']}")
        break
    elif result["data"]["status"] == "failed":
        print("Failed"); break
    time.sleep(3)

JavaScript

const submitRes = await fetch(`${BASE}/qwen3-tts/text-to-speech`, {
  method: "POST",
  headers: { Authorization: `Bearer ${API_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ prompt: "Welcome to AirCube. The unified API for AI generation." }),
});
const { data } = await submitRes.json();

while (true) {
  const poll = await fetch(`${BASE}/status/${data.id}`, {
    headers: { Authorization: `Bearer ${API_KEY}` },
  });
  const result = await poll.json();
  if (result.data.status === "completed") { console.log(`Audio: ${result.data.output_url}`); break; }
  if (result.data.status === "failed") throw new Error("Failed");
  await new Promise((r) => setTimeout(r, 3000));
}

Next steps

Submit Generation — full parameter reference by task type.
Get Result — polling endpoint details and status values.
Models — all models with slugs, tasks, and pricing.

On this page