Vertex AI Veo

Generate videos with Google Cloud Vertex AI and Veo 3.1

Generate videos using GA Veo 3.1 models through Google Cloud Vertex AI.

from praisonaiagents import VideoAgent

agent = VideoAgent(llm="vertex_ai/veo-3.1-generate-001")
video = agent.start("Ocean waves at sunset", output="ocean.mp4")

Authentication

Vertex AI supports two auth paths — pick the one that matches your setup.

# Option A: service account (CI / production)
export GOOGLE_APPLICATION_CREDENTIALS=path/to/service-account.json

# Option B: project + location (local dev with gcloud)
export VERTEXAI_PROJECT=your-project-id
export VERTEXAI_LOCATION=us-central1

Models

Three GA Veo 3.1 tiers cover cinematic quality down to cheap iteration.

Deprecated

Migrate to the veo-3.1 IDs above. These older models are being retired.

Veo 3.1 features

Veo 3.1 adds frame interpolation and reference images. Both pass straight through generate() — no extra setup.

from praisonaiagents import VideoAgent

agent = VideoAgent(llm="vertex_ai/veo-3.1-generate-001")

# First + last frame interpolation (Veo 3.1)
agent.generate(
    prompt="Sunrise timelapse",
    input_reference=start_image,  # first frame
    last_frame=end_image,         # last frame
)

from praisonaiagents import VideoAgent

agent = VideoAgent(llm="vertex_ai/veo-3.1-generate-001")

# Up to 3 reference images
agent.generate(
    prompt="A cinematic dolly shot of the character",
    reference_images=[img1, img2, img3],
)

Pricing & billing

Vertex AI Veo bills per generated second in USD, charged through your connected GCP project.

Parameters

video = agent.generate(
    prompt="Your description"
)

Features