Veo is Google's model for generating videos with audio. You can use this model in the Vertex AI Media Studio or using the Vertex AI video generation API.
Veo can generate the following:
- Videos at 720p, 1080p, or 4K resolution.
- Videos with 16:9 (landscape) or 9:16 (portrait) aspect ratio.
- Clips of 4, 6, or 8 seconds in length.
- Audio and dialogue.
You can also use Veo to extend existing videos, and instruct the model to use specific images as the first and last frame of a video.
Try Veo on Vertex AI Media Studio
Veo model versions
There are multiple Veo video generation models that you can use. For more information, see Veo models.
Key features
Veo 3.1 excels at a wide range of visual and cinematic styles with the following capabilities:
- Text to video
- Image (first frame) to video
- First and last frames to video
- Ingredients to video (with image references)
- Extend videos
- Insert objects
- Remove objects
For more information about writing effective text prompts for video generation, see the Veo prompt guide and Veo best practices.
Locations
A location is a region that you can specify in a request to control where data is stored at rest. For more information about where Veo is available, see Generative AI on Vertex AI locations.
Responsible AI for Veo on Vertex AI
Veo on Vertex AI is designed with Google's AI Principles in mind. However, it's important to understand how to test and deploy Google's models safely and responsibly. Veo on Vertex AI has built-in safety features to help you block potentially harmful outputs within your use cases. For more information, see Responsible AI for Veo.