OpenParable
Skip to content
← Back to skills

Veo

Documents
veo

Veo is an Agent Skill for documents published in the sundial-org/awesome-openclaw-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Generate video using Google Veo (Veo 3.1 / Veo 3.0).

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/sundial-org/awesome-openclaw-skills/blob/HEAD/skills/veo/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/veo, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Veo (Google Video Generation)

Generate video clips using Google's Veo API.

Generate video

uv run {baseDir}/scripts/generate_video.py --prompt "your video description" --filename "output.mp4"

Options

  • --duration / -d: Video duration in seconds (default: 8, max varies by model)
  • --aspect-ratio / -a: Aspect ratio (16:9, 9:16, 1:1)
  • --model: Veo model to use (veo-2.0-generate-001, veo-3.0-generate-001, veo-3.1-generate-preview, etc.)
  • --api-key: Override GEMINI_API_KEY

API key

  • GEMINI_API_KEY env var (preferred)
  • Or set skills."veo".env.GEMINI_API_KEY in ~/.clawdbot/clawdbot.json

Notes

  • Veo 3.1 supports higher quality and longer durations
  • Output is MP4 format
  • Use --model veo-3.1-generate-preview for best results
  • Veo 3.0-fast-generate-001 is faster but lower quality
  • The script prints a MEDIA: line for Clawdbot to auto-attach on supported chat providers.