veo

# Veo Video Generation

Generate high-fidelity videos with Google Veo 3.1 via API. Supports text-to-video, image-to-video, and video-to-video workflows with advanced cinematography control and synchronized audio generation.

## Quick Start

### Installation

```bash
uv pip install google-genai
```

### Basic Generation

```python
from google import genai
from google.genai import types
import time
import os

# Initialize client
client = genai.Client(
    vertexai=True,
    project=os.getenv("GOOGLE_CLOUD_PROJECT"),  # Set via environment variable
    location="us-central1"
)

# Generate video from text
operation = client.models.generate_videos(
    model='veo-3.1-generate-preview',
    prompt='A neon hologram of a cat driving at top speed',
    config=types.GenerateVideosConfig(
        number_of_videos=1,
        duration_seconds=5,
        # enhance_prompt defaults to True and cannot be disabled in Veo 3.1
    ),
)

# Poll until complete (typically 2-5 minutes)
while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)

# Check for errors before accessing response
if operation.error:
    raise Exception(f"Video generation failed: {operation.error}")

# Save the generated video
video = operation.response.generated_videos[0].video
with open('output.mp4', 'wb') as f:
    f.write(video.video_bytes)
```

## Core Capabilities

- **Resolutions:** 720p or 1080p
- **Aspect ratios:** 16:9 or 9:16
- **Clip lengths:** 4, 6, or 8 seconds
- **Rich audio:** Synchronized dialogue, sound effects, ambient noise
- **Advanced controls:** Image-to-video, first/last frame transitions, consistent characters

## The Prompting Formula

For consistent, high-quality results, structure prompts using:

**[Cinematography] + [Subject] + [Action] + [Context] + [Style & Ambiance]**

### Example

```
Medium shot, a tired corporate worker, rubbing his temples in exhaustion,
in front of a bulky 1980s computer in a cluttered office late at night.
The scene is lit by