veo-video

Generate AI videos from text prompts or images via the Google Veo API.

13|1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/AceDataCloud/Skills --skill veo-video-acedatacloud
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: veo-video
Source: https://github.com/AceDataCloud/Skills/tree/main/skills/veo-video
Command: npx skills add https://github.com/AceDataCloud/Skills --skill veo-video-acedatacloud

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of turning text prompts or images into high-quality AI videos, including iterative edits like extending, reshooting, upscaling, and adding/removing objects.

Core Features & Use Cases

  • Text-to-Video & Image-to-Video: Generate cinematic motion from prompts, or animate a still image into a video.
  • Advanced Video Editing: Upscale to 1080p, extend a scene, re-shoot with new camera motion, and insert or remove objects via mask inpainting.
  • Model Choice for Audio & Quality: Use Veo 2 for cost-effective generation, and Veo 3/3.1 for native audio and higher-quality outputs.

Example: You describe a scene in natural language, generate a short video, then extend it and reshoot with different camera motion to match your desired pacing.

Quick Start

Use veo-video to generate a text-to-video clip from a prompt by sending your prompt and selecting a Veo model and output resolution.

Frequently Asked Questions about veo-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI video from text prompts or images using Google Veo?▼

To generate AI video with Google Veo, you submit text prompts or reference images to the API. This process supports text-to-video, image-to-video, and multi-image blending to create cinematic motion.

Can I extend, upscale, or reshoot an AI video after generation?▼

Yes, you can perform post-generation edits like upscaling to 1080p, extending a scene, reshooting with new camera motion, and inserting or removing objects via mask inpainting.

Which Veo models support native audio generation for AI video?▼

Native audio generation for AI video is supported exclusively on Veo 3 and Veo 3.1 models. Veo 2 is available for cost-effective generation but lacks native audio support.

Do I need an API token to generate videos with Google Veo?▼

Yes, you need an ACEDATACLOUD_API_TOKEN for authentication to generate videos with Google Veo. This token enforces action- and model-specific parameter constraints like aspect_ratio.

What are the limitations when using image-to-video with Google Veo?▼

Image-to-video generation with Google Veo requires specific parameter constraints like aspect_ratio. Additionally, native audio is only supported on Veo 3 and 3.1 models, limiting audio features on Veo 2.