home / skills / openclaw / skills / google-veo

google-veo skill

needs review

This skill helps generate high-quality videos using Google Veo models via inference.sh, delivering cinematic results from textual prompts.

npx playbooks add skill openclaw/skills --skill google-veo

Review the files below or copy the command above to add this skill to your agents.

Files (2)

SKILL.md

3.5 KB

---
name: google-veo
description: "Generate videos with Google Veo models via inference.sh CLI. Models: Veo 3.1, Veo 3.1 Fast, Veo 3, Veo 3 Fast, Veo 2. Capabilities: text-to-video, cinematic output, high quality video generation. Triggers: veo, google veo, veo 3, veo 2, veo 3.1, vertex ai video, google video generation, google video ai, veo model, veo video"
allowed-tools: Bash(infsh *)
---

# Google Veo Video Generation

Generate videos with Google Veo models via [inference.sh](https://inference.sh) CLI.

![Google Veo Video Generation](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kg2c0egyg243mnyth4y6g51q.jpeg)

## Quick Start

```bash
curl -fsSL https://cli.inference.sh | sh && infsh login

infsh app run google/veo-3-1-fast --input '{"prompt": "drone shot over a mountain lake"}'
```

> **Install note:** The [install script](https://cli.inference.sh) only detects your OS/architecture, downloads the matching binary from `dist.inference.sh`, and verifies its SHA-256 checksum. No elevated permissions or background processes. [Manual install & verification](https://dist.inference.sh/cli/checksums.txt) available.

## Veo Models

| Model | App ID | Speed | Quality |
|-------|--------|-------|---------|
| Veo 3.1 | `google/veo-3-1` | Slower | Best |
| Veo 3.1 Fast | `google/veo-3-1-fast` | Fast | Excellent |
| Veo 3 | `google/veo-3` | Medium | Excellent |
| Veo 3 Fast | `google/veo-3-fast` | Fast | Very Good |
| Veo 2 | `google/veo-2` | Medium | Good |

## Search Veo Apps

```bash
infsh app list --search "veo"
```

## Examples

### Cinematic Shot

```bash
infsh app run google/veo-3-1-fast --input '{
  "prompt": "Cinematic drone shot flying through a misty forest at sunrise, volumetric lighting"
}'
```

### Product Demo

```bash
infsh app run google/veo-3 --input '{
  "prompt": "Sleek smartphone rotating on a dark reflective surface, studio lighting"
}'
```

### Nature Scene

```bash
infsh app run google/veo-3-1-fast --input '{
  "prompt": "Timelapse of clouds moving over a mountain range, golden hour"
}'
```

### Action Shot

```bash
infsh app run google/veo-3 --input '{
  "prompt": "Slow motion water droplet splashing into a pool, macro shot"
}'
```

### Urban Scene

```bash
infsh app run google/veo-3-1-fast --input '{
  "prompt": "Busy city street at night with neon signs and rain reflections, Tokyo style"
}'
```

## Prompt Tips

**Camera movements**: drone shot, tracking shot, pan, zoom, dolly, steadicam

**Lighting**: golden hour, blue hour, studio lighting, volumetric, neon, natural

**Style**: cinematic, documentary, commercial, artistic, realistic

**Timing**: slow motion, timelapse, real-time

## Sample Workflow

```bash
# 1. Generate sample input to see all options
infsh app sample google/veo-3-1-fast --save input.json

# 2. Edit the prompt
# 3. Run
infsh app run google/veo-3-1-fast --input input.json
```

## Related Skills

```bash
# Full platform skill (all 150+ apps)
npx skills add inference-sh/skills@inference-sh

# All video generation models
npx skills add inference-sh/skills@ai-video-generation

# AI avatars & lipsync
npx skills add inference-sh/skills@ai-avatar-video

# Image generation (for image-to-video)
npx skills add inference-sh/skills@ai-image-generation
```

Browse all video apps: `infsh app list --category video`

## Documentation

- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI
- [Streaming Results](https://inference.sh/docs/api/sdk/streaming) - Real-time progress updates
- [Content Pipeline Example](https://inference.sh/docs/examples/content-pipeline) - Building media workflows

Overview

This skill lets you generate high-quality videos using Google Veo models through the inference.sh CLI. It exposes multiple Veo model variants (Veo 3.1, Veo 3.1 Fast, Veo 3, Veo 3 Fast, Veo 2) so you can trade off speed and quality. Use simple CLI commands to run text-to-video jobs and retrieve cinematic output for demos, marketing, or creative projects.

How this skill works

Install and authenticate the inference.sh CLI, then run an app with an input JSON or inline prompt to invoke a specific Veo model. The CLI handles request submission, job monitoring, and result retrieval; models return rendered video artifacts. Select faster model variants for quick iterations and higher‑quality models for final renders.

When to use it

Create short cinematic clips from text prompts for marketing or social media.
Produce product demo videos with controlled lighting and camera styles.
Generate nature, urban, or action scenes without a physical shoot.
Iterate rapidly on visual concepts using fast model variants.
Export final-quality footage by choosing the highest-quality Veo 3.1 model.

Best practices

Start with short prompts and iterate: test with Veo 3.1 Fast, then switch to Veo 3.1 for final render.
Include camera movement, lighting, and timing keywords (e.g., drone shot, volumetric lighting, slow motion).
Save and edit sample input JSON from the CLI to fine-tune complex prompts and parameters.
Use modular prompts for multi-stage workflows (storyboard -> test -> polish) to control costs.
Monitor progress via CLI streaming to stop or adjust runs early if needed.

Example use cases

Cinematic drone shot over a mountain lake at sunrise for a travel promo.
Studio-style product rotation for an e-commerce demo of a smartphone.
Timelapse of clouds across a mountain range for background footage.
Slow-motion macro of water droplets for a commercial or scientific illustration.
Nighttime urban street scene with neon reflections for a music video or short film.

FAQ

How do I choose between Veo 3.1 and Veo 3.1 Fast?

Use Veo 3.1 Fast for quick iterations and Veo 3.1 for the highest final quality when time and cost allow.

What format do results come in and how do I retrieve them?

Results are returned as video artifacts by the inference.sh app run command; the CLI downloads or exposes URLs for the rendered files.