Generate a video

Text to video is a single request. In the example below, MiniMax H3 takes a prompt, a length in seconds, a quality tier, and an aspect ratio.

curl -X POST https://api.protoface.com/v1/run/minimax/minimax-h3 \
  -H "Authorization: Bearer $PROTOFACE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A wide shot of a sailboat crossing a quiet bay at sunrise.",
    "duration_seconds": 8,
    "quality": "768p",
    "aspect_ratio": "16:9"
  }'

The request returns a run ID immediately. The clip lands on video.url once status reaches completed.

curl https://api.protoface.com/v1/runs/run_... \
  -H "Authorization: Bearer $PROTOFACE_API_KEY"

{
  "id": "run_...",
  "status": "completed",
  "video": {
    "url": "https://...",
    "content_type": "video/mp4",
    "file_name": "output.mp4"
  }
}

Bodies are not portable between video models. duration_seconds and quality are MiniMax H3’s names. Most models use duration and resolution, and models with several operations require operation. Build each body from its request schema.

Inference

Realtime

Account

Reference