skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

google-veo

Generate videos from text prompts using Google Veo models via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#cli#video generation#text-to-video#inference.sh#ai video#google veo#veo 3
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill google-veo-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: google-veo
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/google-veo
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill google-veo-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating video content traditionally requires filming equipment, editing software, and significant production time. This Skill lets you generate videos directly from text prompts using Google's Veo models through the inference.sh CLI, removing the need for manual video production. ## Core Features & Use Cases - Multiple Veo Models: Choose from Veo 3.1, Veo 3.1 Fast, Veo 3, Veo 3 Fast, and Veo 2 to balance generation speed against output quality. - Text-to-Video Generation: Produce cinematic shots, product demos, nature scenes, action shots, and urban scenes from descriptive prompts. - Prompt Guidance: Built-in tips for camera movements, lighting, style, and timing help you write effective generation prompts. - Use Case: A marketing team needs a short product teaser video. They run the Veo 3 model with a prompt describing a smartphone rotating on a reflective surface with studio lighting, and receive a generated clip without any filming. ## Quick Start Ask the AI to generate a video with Google Veo using a prompt like "drone shot over a mountain lake" via the inference.sh belt CLI.

Frequently Asked Questions about google-veo

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

FAQPage Schema
How do I generate a video with Google Veo from the command line?▼

Install the inference.sh belt CLI, run belt login to authenticate, then execute belt app run with a Veo app ID such as google/veo-3-1-fast and a JSON input containing your text prompt.

What is the difference between Veo 3.1, Veo 3, and Veo 2?▼

Veo 3.1 offers the best quality at slower speed, Veo 3.1 Fast and Veo 3 Fast prioritize faster generation with excellent to very good quality, and Veo 2 provides good quality at medium speed. Choose based on your speed versus quality needs.

How do I write better prompts for Veo video generation?▼

Include camera movements like drone shot or tracking shot, lighting terms like golden hour or studio lighting, a style such as cinematic or documentary, and timing like slow motion or timelapse. Combining these elements produces more controlled results.

Does Google Veo generation require an inference.sh account?▼

Yes, the Veo models run through the inference.sh platform. You must install the belt CLI and authenticate with belt login before running any Veo app.

How can I see all available input options for a Veo model?▼

Run belt app sample with the app ID and the --save flag, for example belt app sample google/veo-3-1-fast --save input.json. This writes a sample input file you can edit before running the generation.

Related Skills

Explore More Design & Creative Skills→
pingdiorpingdior
7

text-to-image-prompt-gen3-runway

Generate Runway Gen-3 Alpha text prompts with camera, lighting, and motion instructions.

Community
Intermediate
irismakerirismaker

video

Create marketing videos with AI avatars, generated footage, and programmatic overlays.

Community
Advanced
phrazzldphrazzld
13

ai-media

Generate images, videos, and voiceovers via inference.sh CLI and Remotion.

Community
Advanced
inference-shinference-sh
688

google-veo

Generate videos from text prompts using Google Veo models via inference.sh CLI.

Official
Intermediate