Veo

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

Video generation with Veo is currently in public preview.

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

Text-to-video generation

Generate videos from text prompts:

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:

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

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.

Generate videos by extending or modifying existing videos:

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:

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:

video = types.Video(
    uri="gs://bucket-name/inputs/videos/cat_driving.mp4",
)