
Written By Deepti Ratnam
Published By: Deepti Ratnam | Published: May 21, 2025, 11:30 AM (IST)
Google hosted its annual event, dubbed Google I/O, on 19 May, introducing and announcing several enhanced and powerful features and tools that change how we perceive AI, New Apps, and many other interesting things. The tech giant revealed the next evolution in its AI video technology and that is Veo 3. It is a powerful model that now brings sound into the mix. The tool is built upon the foundation laid by its predecessor, Veo 2, the latest version introduces audio generation as a key feature.
Veo 3 is a new video tool that produces realistic background noises, sound effects, and even spoken dialogue in sync with the visuals it creates. This new development by Google marks a major leap forward for the AI-generated videos where both image and sound plays an important role and are created in harmony.
Veo 3 will be rolled out starting Tuesday for users in the United States via its Gemini app. However, there is a catch and hence it is exclusively available to users who have subscribed to the 249.99-per-month AI Ultra plan. Other than available via Gemini, Veo 3 will also be integrated into the Google’s Vortex AI platform. This platform is designed for enterprise customers.
You just have to prompt the AI with either text descriptions or images and the model will respond with full video clips and complete with audio elements.
Veo 3 is designed in such a way that it doesn’t only offer sound, it also delivers noticeable improvements in video quality over Veo 2. These improvements can be seen especially in areas like visual realism, motion, and lip-sync accuracy.
There are several features available in Veo 3, whether its replicating the ambient sounds or even rendering a believable conversation between on-screen characters, the Veo 3 model exhibits a stronger understanding of natural settings and storytelling.
Additionally, the tool also responds to the longer and more complex prompts. It also generates clips that are following a structured sequence of events. It give creators more narrative flexibility than ever before.
Say goodbye to the silent era of video generation: Introducing Veo 3 — with native audio generation. 🗣️
Quality is up from Veo 2, and now you can add dialogue between characters, sound effects and background noise.
Veo 3 is available now in the @GeminiApp for Google AI Ultra… pic.twitter.com/7rcXeBslyU
— Google (@Google) May 20, 2025
Alongside the launch of the Veo 3, the company also added some new features and updated Veo 2 based on the feedback from professional filmmakers and creators. Among the latest capabilities are reference-based video generation, Camera movement controls, outpainting, addition or removal of objects, and more. These tools further solidify Google’s video AI ecosystem as a comprehensive suite for creative professionals.
Veo 3 is giving tough competition to OpenAI’s Sora that made waves in the AI video space. However, as per Google, Veo 3 positions itself with a major advantage due to its built-in audio generation feature. This feature gives Google’s model an edge when it comes to creating immersive and complete video package experience.
According to Matthieu Lorrain, creative lead at Google DeepMind, Veo 3 is not only easier to prompt than previous versions, but it’s also more adept at interpreting longer scripts and chaining multiple events together fluidly within a clip.
At #GoogleIO, we shared how decades of AI research have now become reality.
From a total reimagining of Search to Agent Mode, Veo 3 and more, Gemini season will be the most exciting era of AI yet.
Some highlights 🧵 pic.twitter.com/2n9rbGNj0Q
— Sundar Pichai (@sundarpichai) May 20, 2025
Talking about other enhanced features that level up the Veo 3 is that it doesn’t just include audio or dialogue, it also has the ability to include animal sounds, environmental ambience, and subtle audio cues. All these features together generated in synch with the visual content and making the Veo 3 as one of the most comprehensive AI tools of its kind.
In addition to Veo 3, Google unveiled other AI-powered tools at I/O 2025 including Imagen 4 which can be accessed via Gemini, Whisk, Vertex AI, and Workspace.