Summary  
This chapter covers prompt engineering by structuring text-to-video inputs into four components—subject, action, setting, and style/camera—to guide a generative system toward precise results.  

General domain of usage  
AI-driven video generation

A good Veo prompt reads like a film direction, not a search query. Structure it in four parts: subject, action, setting, style/camera.


A golden retriever puppy chasing a red ball across a sunlit park lawn, slow-motion, warm afternoon light, shot on a 50mm lens.

Vague prompts get generic results. Specific, concrete details give the model something to actually render.

Note

```
A ceramic coffee mug rotating slowly on a marble surface, soft studio lighting, minimal background, product photography style.
```

Product Demo

```
Aerial drone shot flying over a misty pine forest at sunrise, camera slowly descending toward the treetops.
```

Nature Scene

```
A woman in a cozy kitchen looks at the camera and says, "Let's get started." Medium shot, warm morning light.
```

Dialogue

AI video generation has moved from novelty to everyday creative tool — and Google Veo 3.1 is currently the most capable model you can access for free. This mini-course teaches you to go from a blank prompt box to a finished, publish-ready video clip. Across 10 short lessons, you'll learn to write prompts that actually work, generate built-in dialogue and sound effects, keep the same character consistent across multiple shots, and export the right format for YouTube, TikTok, or Instagram. No editing software or technical background required — just a browser and an idea.

Writing Your First Text-to-Video Prompt

Prompt Examples