Today, we are releasing Veo 3.1 and Veo 3.1 Fast in paid preview in the Gemini API. This updated model offers several improvements, as well as improved outputs when generating video from images. These new models are available via the Gemini API in Google AI Studio and Vertex AI. Veo 3.1 is also available in the Gemini app and Flow.
Veo 3.1: our improved video generation model
Veo 3.1 and Veo 3.1 Fast empower developers to create more engaging content through significant upgrades. The models now generate richer native audio, from natural conversations to synchronized sound effects, and offer greater narrative control with an improved understanding of cinematic styles. Enhanced image-to-video capabilities ensure better prompt adherence while delivering superior audio and visual quality and maintaining character consistency across multiple scenes.
In addition to the model update, we are introducing new model capabilities, including using reference images to guide video generation, extend existing Veo videos, and generate transitions between a first and last frame.
Guide generation with ‘Ingredients to video’
You can now guide the generation process by providing up to 3 reference images of a character, object, or scene. This is helpful for maintaining character consistency across multiple shots or applying a specific style to your video.
from google import genai
from google.genai import types
client = genai.Client()
operation = client.models.generate_videos(
model="veo-3.1-generate-preview",
prompt=prompt,
config=types.GenerateVideosConfig(
reference_images=[reference_image1, reference_image2],
),
)Python
See more in the documentation.
Create longer videos with ‘Scene extension’
Your story is no longer limited by the original generation. With Scene extension, you can create longer videos, even lasting for a minute or more, by generating new clips that connect to your previous video. Each new video is generated based on the final second of the previous clip. This maintains visual continuity, making the feature ideal for extending shots with background audio.
from google import genai
client = genai.Client()
operation = client.models.generate_videos(
model="veo-3.1-generate-preview",
prompt=prompt,
video=video_to_extend
)Python
See more in the documentation.
Control your video with ‘First and last frame’
Create smooth, natural scenes that bridge two different images. By providing a starting and an ending image, you can direct Veo 3.1 to generate the transition between them, complete with accompanying audio.
from google import genai
from google.genai import types
client = genai.Client()
operation = client.models.generate_videos(
model="veo-3.1-generate-preview",
prompt=prompt,
image=first_frame,
config=types.GenerateVideosConfig(
last_frame=last_frame,
),
)Python
See more in the documentation.
What people are building with Veo 3.1
Promise Studios, a GenAI movie studio, uses Veo 3.1 within its MUSE Platform to enhance generative storyboarding and previsualization for director-driven storytelling at production quality.
Latitude is experimenting with Veo 3.1 in its generative narrative engine to instantly bring user-created stories to life.
Start building today
Veo 3.1 and these new capabilities are now available in paid preview via the Gemini API.
- Dive into the documentation for detailed parameter information and video length control,
- Start using Veo 3.1 and the new features in Veo Studio, our new AI Studio demo app (paid Gemini API key required)
- Or jump right into the code with the updated cookbook guide
Veo 3.1 is the same price as Veo 3. We are incredibly excited to see what you will build with these new capabilities!
