Google DeepMind Launches Veo 3.1 with Enhanced Audio and Texture Features
Google DeepMind has announced the release of the new version of its video generation model, Veo 3.1, which will delight users with improved image quality, enhanced text prompts, and more realistic texture rendering.
The key changes in Veo 3.1, now part of the Flow update—a tool for AI-based video creation—include the integration of audio into all its features. Thanks to the capabilities of Ingredients to Video, Frames to Video, and Extend, users can now enrich their videos with a sound atmosphere, providing a more cinematic presentation. Since its launch just five months ago, Flow has already generated over 275 million clips.
In addition, Flow has gained new editing capabilities—Insert and Remove functions, which make adding or removing elements in videos easier without noticeable editing traces. The Veo 3.1 model is now available through the Gemini API, Vertex AI for businesses, and in the Gemini app.
This development is part of a broader trend toward integrating artificial intelligence into creative processes, allowing not only for reduced content production time but also for enhanced quality. Although the earlier application of Veo in video advertising allegedly caused mixed reactions among Taylor Swift fans due to rumors of its use, there was no direct evidence of this.
| Function | Description |
|---|---|
| Ingredients to Video | Adding a sound atmosphere to videos |
| Frames to Video | Sound accompaniment during transitions between frames |
| Extend | Extending scenes while preserving the sound atmosphere |
| Insert | Adding new objects or characters |
| Remove | Removing unnecessary elements with automatic background restoration |
