// Generates AI videos from text prompts or reference images using OpenAI Sora. Use when the user wants to create videos, generate video clips, make AI films, animate images, or produce motion content. Supports text-to-video, image-to-video, and video remixing.
| name | sora-video |
| description | Generates AI videos from text prompts or reference images using OpenAI Sora. Use when the user wants to create videos, generate video clips, make AI films, animate images, or produce motion content. Supports text-to-video, image-to-video, and video remixing. |
Generate high-quality AI videos using OpenAI's Sora model.
Before using this skill, ensure:
Python packages are installed:
pip install openai
API key is set:
export OPENAI_API_KEY="your-openai-api-key"
Get your key at: https://platform.openai.com/api-keys
Generate a video from a text description:
python skills/sora-video/scripts/generate_video.py --prompt "A drone shot flying over a misty forest at sunrise" --output forest.mp4
Animate a reference image:
python skills/sora-video/scripts/generate_video.py --prompt "The scene comes to life with gentle wind" --input photo.jpg --output animated.mp4
Use the pro model for production-grade quality:
python skills/sora-video/scripts/generate_video.py --prompt "A cinematic sunset over mountains" --model sora-2-pro --size 1792x1024 --seconds 12 --output cinematic.mp4
| Argument | Short | Required | Default | Description |
|---|---|---|---|---|
--prompt | -p | Yes | -- | Text description of the desired video |
--output | -o | No | generated_video.mp4 | Output file path |
--input | -i | No | -- | Reference image for image-to-video mode |
--model | -m | No | sora-2 | Model: sora-2 or sora-2-pro |
--seconds | -s | No | 8 | Duration: 4, 8, or 12 |
--size | No | 1280x720 | Resolution (see table below) | |
--timeout | No | 600 | Max wait time in seconds |
| Size | Orientation | Models |
|---|---|---|
1280x720 | Landscape | sora-2, sora-2-pro |
720x1280 | Portrait | sora-2, sora-2-pro |
1792x1024 | Landscape HD | sora-2-pro only |
1024x1792 | Portrait HD | sora-2-pro only |
For best results:
Nature:
A drone shot flying over a misty forest at sunrise, golden light filtering through
the trees, birds rising from the canopy, cinematic quality
Urban:
A time-lapse of a busy Tokyo intersection at night, neon signs reflecting on wet
pavement, crowds crossing in all directions, cyberpunk atmosphere
Abstract:
Liquid metal flowing and morphing into geometric shapes, iridescent reflections,
dark background, smooth motion, high-end product visualization style
| Model | Resolution | Per Second | 4s Clip | 8s Clip | 12s Clip |
|---|---|---|---|---|---|
| sora-2 | 720p | $0.10 | $0.40 | $0.80 | $1.20 |
| sora-2-pro | 720p | $0.30 | $1.20 | $2.40 | $3.60 |
| sora-2-pro | 1024p | $0.50 | $2.00 | $4.00 | $6.00 |
Note: You are charged for every generation attempt, including failed ones.
--input"OPENAI_API_KEY not set"
export OPENAI_API_KEY="your-key""openai package not installed"
pip install openai"Video generation failed: content_policy_violation"
"Video generation timed out"
--timeout 900sora-2 (faster) instead of sora-2-pro"Rate limit exceeded"
The script will: