Google has unveiled Veo 3, an advanced AI-powered video creation tool that not only generates visuals but also integrates audio seamlessly. Unlike competing platforms such as OpenAI’s Sora, Veo 3 sets itself apart with its ability to embed audio directly into the videos it produces. According to Google, the tool can generate a range of sounds—including character dialogue and animal noises—enhancing the realism and storytelling of AI-generated content.
Veo 3 Launches with Advanced Audio-Visual AI Capabilities:
Google has introduced Veo 3, a cutting-edge video generation tool capable of producing highly realistic background sounds, sound effects, and even synchronized spoken dialogue to match the visuals it creates. This marks a significant advancement in AI-driven video production, where both imagery and audio are developed in seamless unison.
Already impressed with what you all are making in Veo 3. Some creative ones spotted by our team below ⬇️
We’ll keep adding to this thread, so keep sharing and tagging us. https://t.co/fv3NboUvgR
— Google Gemini App (@GeminiApp) May 21, 2025
Veo 3 Access and Availability:
Starting Tuesday, Veo 3 will become accessible in the United States through the Gemini app. However, access is limited to subscribers of the premium AI Ultra plan, which costs $249.99 per month. In addition to Gemini, Veo 3 will also be incorporated into Google’s enterprise-focused Vortex AI platform, targeting business and professional users.
Veo 3 Major Features:
Veo 3 goes beyond simply adding sound—it also introduces significant upgrades in video quality compared to its predecessor, Veo 2. These enhancements are particularly evident in areas such as visual realism, smoother motion, and more accurate lip-syncing.
The tool comes packed with powerful features. Whether it’s recreating ambient noises or crafting lifelike conversations between characters, Veo 3 demonstrates a deeper grasp of real-world environments and cinematic storytelling.
Video, meet audio. 🎥🤝🔊
With Veo 3, our new state-of-the-art generative video model, you can add soundtracks to clips you make.
Create talking characters, include sound effects, and more while developing videos in a range of cinematic styles. 🧵 pic.twitter.com/5Hfpetfg8b
— Google DeepMind (@GoogleDeepMind) May 20, 2025
Moreover, it can interpret and respond to longer, more detailed prompts, producing video clips that follow a coherent and structured narrative. This gives creators greater freedom to develop complex storylines
Google has also enhanced its Veo 2 video generation tool by introducing a new feature that lets users insert or delete objects within a video using simple text commands. In addition, the company has made its Lyria 2 music-generation model available to content creators via the YouTube Shorts platform, as well as to enterprise users through the Vertex AI system.
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