video-generation
Video Generation: Create videos with Veo
Overview
Generate videos using Google's Veo models. Supports:
- Text-to-video generation (4-8 seconds)
- Image-to-video (animate a starting frame)
- Native audio generation with dialogue and sound effects (Veo 3.1)
Reference: https://ai.google.dev/gemini-api/docs/video
How to use
bash ${CLAUDE_PLUGIN_ROOT}/scripts/gemini.sh --model=veo-3.1-generate-preview "YOUR VIDEO DESCRIPTION"
Arguments:
--model- Required: Use a Veo model (see Models below)--file- Optional: Starting frame image for image-to-video--aspect-ratio- Optional:16:9(default) or9:16--duration- Optional:4,6, or8seconds (default: 8)
Examples:
# Generate a video from text
npx -y superconductor-gemini-skills --model=veo-3.1-generate-preview "A serene mountain landscape at sunset, camera slowly panning right"
# Generate with specific aspect ratio and duration
npx -y superconductor-gemini-skills --model=veo-3.1-generate-preview --aspect-ratio=9:16 --duration=4 "A person walking through a busy city street"
# Include dialogue (Veo 3.1)
npx -y superconductor-gemini-skills --model=veo-3.1-generate-preview "Two friends at a coffee shop. One says \"Did you hear the news?\" The other replies \"No, what happened?\""
# Animate an image
npx -y superconductor-gemini-skills --model=veo-3.1-generate-preview --file=landscape.jpg "Camera slowly zooms in on the mountain peak"
# Fast generation (lower quality, quicker)
npx -y superconductor-gemini-skills --model=veo-3.1-fast-generate-preview "A cat playing with a ball of yarn"
Prompt tips
Effective prompts should include:
- Subject: What appears in the video
- Action: What the subject does
- Style: Creative direction (cinematic, documentary, etc.)
- Camera: Movement and positioning (pan, zoom, tracking shot)
- Audio (Veo 3.1): Dialogue in quotes, sound effect descriptions
Output
Generated videos are saved to the current directory as gemini-video-{timestamp}.mp4.
Limitations
- Video length: 4-8 seconds
- Generation time: 11 seconds to 6 minutes
- Videos stored on server for 2 days
- All videos include SynthID watermarks
API Key
The GEMINI_API_KEY environment variable must be set. Get your key at: https://ai.google.dev/gemini-api/docs/api-key
Models
| Model ID | Features | Speed |
|---|---|---|
veo-3.1-generate-preview |
Native audio, best quality | Normal |
veo-3.1-fast-generate-preview |
Native audio, faster | Fast |
veo-3.0-generate-001 |
Audio support | Normal |
More from superconductor/superconductor-plugin-marketplace
video-understanding
Analyze and understand video content using Google Gemini. Supports local video files (mp4, mov, webm, avi, mkv) and YouTube links up to an hour long. Use this skill when you need to understand, summarize, or extract information from video content.
9audio-understanding
Transcribe and analyze audio content using Google Gemini. Supports local audio files (mp3, wav, m4a, ogg, flac) and YouTube links up to 9.5 hours long. Use this skill when you need to transcribe, summarize, or extract information from audio content.
5x-api
Interact with the X (Twitter) API v2 using curl commands. Use this skill to look up user profiles, search recent posts, retrieve tweets, get user timelines, and explore other public X API v2 endpoints.
4image-generation
Generate high-quality images using Google Gemini's Nano Banana Pro image model. Use this skill when you need to create images from text descriptions or transform existing images/videos into new artwork.
4text-to-speech
Convert text to natural-sounding speech using Google Gemini TTS models. Supports 30 different voices and 24 languages. Use this skill when you need to generate audio narration, voiceovers, or spoken content from text.
4gemini-consultation
Ask questions to Google Gemini AI models. Use this skill when you need a second opinion from another frontier AI model, want to analyze documents (PDFs, images), or need Gemini's perspective on any topic.
4