> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/googleapis/python-genai/llms.txt
> Use this file to discover all available pages before exploring further.

# Veo

> Generate videos using text-to-video, image-to-video, and video-to-video with Veo models

<Warning>
  Video generation with Veo is currently in public preview.
</Warning>

Veo models enable you to generate videos from text prompts, images, or existing videos.

## Text-to-video generation

Generate videos from text prompts:

```python theme={null}
import time
from google.genai import types

# Create operation
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=True,
    ),
)

# Poll operation
while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)

video = operation.response.generated_videos[0].video
video.show()
```

## Image-to-video generation

Generate videos from a starting image:

```python theme={null}
import time
from google.genai import types

# Read local image (uses mimetypes.guess_type to infer mime type)
image = types.Image.from_file("local/path/file.png")

# Create operation
operation = client.models.generate_videos(
    model='veo-3.1-generate-preview',
    # Prompt is optional if image is provided
    prompt='Night sky',
    image=image,
    config=types.GenerateVideosConfig(
        number_of_videos=1,
        duration_seconds=5,
        enhance_prompt=True,
        # Can also pass an Image into last_frame for frame interpolation
    ),
)

# Poll operation
while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)

video = operation.response.generated_videos[0].video
video.show()
```

## Video-to-video generation

<Note>
  Currently, only Gemini Developer API supports video extension on Veo 3.1 for previously generated videos. Vertex AI supports video extension on Veo 2.0.
</Note>

Generate videos by extending or modifying existing videos:

```python theme={null}
import time
from google.genai import types

# Read local video (uses mimetypes.guess_type to infer mime type)
video = types.Video.from_file("local/path/video.mp4")

# Create operation
operation = client.models.generate_videos(
    model='veo-3.1-generate-preview',
    # Prompt is optional if Video is provided
    prompt='Night sky',
    # Input video must be in GCS for Vertex or a URI for Gemini
    video=types.Video(
        uri="gs://bucket-name/inputs/videos/cat_driving.mp4",
    ),
    config=types.GenerateVideosConfig(
        number_of_videos=1,
        duration_seconds=5,
        enhance_prompt=True,
    ),
)

# Poll operation
while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)

video = operation.response.generated_videos[0].video
video.show()
```

## Configuration options

The `GenerateVideosConfig` supports:

* **number\_of\_videos** - Number of videos to generate
* **duration\_seconds** - Video duration (e.g., 5, 10)
* **enhance\_prompt** - Automatically enhance the prompt for better results
* **last\_frame** - Provide an ending frame for frame interpolation

## Polling long-running operations

Video generation is an asynchronous operation. Poll the operation status:

```python theme={null}
import time

while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)

if operation.error:
    print(f"Error: {operation.error}")
else:
    video = operation.response.generated_videos[0].video
    video.show()
```

## GCS paths for Vertex AI

When using Vertex AI, input videos must be stored in Google Cloud Storage:

```python theme={null}
video = types.Video(
    uri="gs://bucket-name/inputs/videos/cat_driving.mp4",
)
```