Google's latest development, Veo 3, debuts at the I/O 2025 conference, allowing users to create AI-generated videos with synchronized audio. The model can produce realistic ambient sounds and human voices, enhancing immersion in generated scenes, such as a subway car. It mimics real-world physics and offers lip-syncing features. This innovation positions Veo 3 among the first of its kind in the industry and is available for Gemini Ultra users in the US. The tool is part of Google's expanding suite of AI resources aimed at creative professionals.
At its annual I/O developer conference, Google unveiled Veo 3, an AI video-generating model capable of creating synchronized audio to enhance realism in generated videos.
Veo 3’s ability to produce video and audio concurrently represents a significant leap in AI technology, aiming to support filmmakers and creative industries more effectively.
Collection
[
|
...
]