Sora Video Generation

Generate videos using OpenAI's Sora API. Use when the user asks to generate, create, or make videos from text prompts or reference images. Supports image-to-video generation with automatic resizing.

Security Scan

The skill appears to implement video generation with OpenAI's Sora API as claimed, but there are mismatches (notably it uses an OpenAI API key despite the registry listing no required credentials) and small packaging/metadata inconsistencies you should review before installing.

Purpose & Capability

Name/description match the implementation: the script calls an OpenAI client to create/retrieve videos and downloads content. However, the registry metadata declares no required credentials while the script clearly requires an OpenAI API key (OPENAI_API_KEY or --api-key). That mismatch is unexpected and should have been declared.

Instruction Scope

SKILL.md and the script stay within the stated purpose: they accept prompt/image, resize images locally, call the Sora video create/retrieve endpoints, poll status, and download the resulting MP4. The script only reads the provided input image path, writes the output file, and uses the provided or environment API key — it does not attempt to read other system files or contact unknown hosts.

Install Mechanism

This is instruction-only (no install spec). The script lists dependencies in comments (openai, httpx, pillow) but there is no automated install step; that is not dangerous but is an operational omission — users must install dependencies themselves. No downloads from unknown URLs or extracted archives are present.

Credentials

The script requires an OpenAI API key (OPENAI_API_KEY or --api-key) to function. The registry metadata does not list any required env vars or primary credential, creating a discrepancy. Aside from the OpenAI key, no other secrets or unrelated env vars are requested, which is proportionate.

Persistence & Privilege

The skill is not always-enabled and has no install-time persistence behavior or attempts to modify other skills or system-wide config. It does not request elevated or persistent privileges.

What to consider before installing

Key points to consider before installing: - This tool will send your prompts and any reference images to OpenAI's video endpoints and requires your OpenAI API key (OPENAI_API_KEY or --api-key). The registry metadata failing to declare this is an inconsistency you should confirm with the publisher before proceeding. - The included script depends on Python packages (openai, httpx, pillow) but there is no install step — install those in a controlled environment (virtualenv) before running. - The script only talks to api.openai.com and saves the returned MP4; it does not contact other endpoints or exfiltrate unspecified data, based on the provided files. - Verify you are comfortable providing your OpenAI API key to this code; consider creating a dedicated API key with limited billing/quota for use with third-party skills. - If you need higher assurance, request the publisher to update registry metadata to declare OPENAI_API_KEY and to provide a reproducible install spec (requirements.txt or install script) and/or review their ownership/source (homepage is missing).

Generate videos using OpenAI's Sora API.

API Reference

Endpoint: POST https://api.openai.com/v1/videos

Parameters

Parameter	Values	Description
prompt	string	Text description of the video (required)
input_reference	file	Optional image that guides generation
model	sora-2, sora-2-pro	Model to use (default: sora-2)
seconds	4, 8, 12	Video duration (default: 4)
size	720x1280, 1280x720, 1024x1792, 1792x1024	Output resolution

Important Notes

• Image dimensions must match video size exactly - the script auto-resizes
• Video generation takes 1-3 minutes typically
• Videos expire after ~1 hour - download immediately

Usage

# Basic text-to-video
uv run ~/.clawdbot/skills/sora/scripts/generate_video.py \
  --prompt "A cat playing piano" \
  --filename "output.mp4"

# Image-to-video (auto-resizes image)
uv run ~/.clawdbot/skills/sora/scripts/generate_video.py \
  --prompt "Slow dolly shot, steam rising, warm lighting" \
  --filename "output.mp4" \
  --input-image "reference.png" \
  --seconds 8 \
  --size 720x1280

# With specific model
uv run ~/.clawdbot/skills/sora/scripts/generate_video.py \
  --prompt "Cinematic scene" \
  --filename "output.mp4" \
  --model sora-2-pro \
  --seconds 12

Script Parameters

Flag	Description	Default
--prompt, -p	Video description (required)	-
--filename, -f	Output file path (required)	-
--input-image, -i	Reference image path	None
--seconds, -s	Duration: 4, 8, or 12	8
--size, -sz	Resolution	720x1280
--model, -m	sora-2 or sora-2-pro	sora-2
--api-key, -k	OpenAI API key	env var
--poll-interval	Check status every N seconds	10

API Key

Set OPENAI_API_KEY environment variable or pass --api-key.

Prompt Engineering for Video

Good prompts include:

1. Camera movement: dolly, pan, zoom, tracking shot
2. Motion description: swirling, rising, falling, shifting
3. Lighting: golden hour, candlelight, dramatic rim lighting
4. Atmosphere: steam, particles, bokeh, haze
5. Mood/style: cinematic, commercial, lifestyle, editorial

Example prompts:

Food commercial:

Slow dolly shot of gourmet dish, soft morning sunlight streaming through window, 
subtle steam rising, warm cozy atmosphere, premium food commercial aesthetic

Lifestyle:

Golden hour light slowly shifting across mountains, gentle breeze rustling leaves, 
serene morning atmosphere, premium lifestyle commercial

Product shot:

Cinematic close-up, dramatic lighting with warm highlights, 
slow reveal, luxury commercial style

Workflow: Image → Video

1. Generate image with Nano Banana Pro (or use existing)
2. Pass image as --input-image to Sora
3. Write prompt describing desired motion/atmosphere
4. Script auto-resizes image to match video dimensions

Output

• Videos saved as MP4
• Typical file size: 1.5-3MB for 8 seconds
• Resolution matches --size parameter