| name | veo |
| description | Generate short videos from text or image prompts using Google's Veo model. Use when the user asks to create a video, generate a clip, or animate an image. |
| compatibility | Gemini CLI |
| metadata | {"version":0.1} |
Veo Video Generation
This skill uses a Python script to generate videos via the Google Veo API, leveraging pre-existing code from the user's genai-googlecloud-scripts repository.
Workflow
- Get Prompt: The user provides a text prompt and optionally an input image.
- Generate Video: Call the main script to handle video generation.
- Return Video: The script will output a
MEDIA: path that OpenClaw will automatically render in the chat.
Usage
Execute the bundled Python script with the desired prompt. The script handles API authentication, initiates the generation, polls for completion, and saves the final video file.
Basic text-to-video:
python {baseDir}/scripts/generate_video.py "A capybara relaxing in a hot spring"
Image-to-video:
python {baseDir}/scripts/generate_video.py "Make this capybara swim" -i /path/to/capybara.jpg
