Documentation

Welcome to the AirCube documentation. AirCube gives developers a single REST API to run state-of-the-art AI models for image generation, video creation, audio synthesis, and face swapping — with no SDK required.

What you can build

• Image generation — generate and edit images with models like Seedream, Flux, GPT Image, and more.
• Video generation — create videos from text or images using Kling, Seedance, Veo, and Sora.
• Audio generation — synthesize speech and music with ElevenLabs, Qwen3 TTS, and MiniMax Music.
• Face swap — swap faces in images and videos with a two-step detect + swap workflow.

Quick example

Submit a generation request, then poll for the result:

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 cinematic photo of a blue geometric cube, studio lighting",
    "aspect_ratio": "16:9"
  }'

{
  "success": true,
  "data": {
    "id": "gen_abc123def456",
    "status": "processing",
    "model": "Seedream 5.0 Pro",
    "type": "image",
    "output_url": null,
    "created_at": "2025-01-15T12:00:00.000Z"
  }
}

curl https://aircube.ai/api/v3/status/gen_abc123def456 \
  -H "Authorization: Bearer $AIRCUBE_API_KEY"

Next steps

• Getting Started — understand how the API works and make your first request.
• API Reference — detailed endpoint documentation.
• Model catalog — browse all available models.
• Pricing — see per-generation pricing for every model.