Revolution in content creation: Veo 3 generates dialogues and sound effects

Google has introduced Veo 3 — the latest video generation model, which deservedly can be called a real breakthrough in this field. The main feature of this technology is full sound support. If previously generative videos were predominantly silent or required separate audio processing, now the system creates videos with sound effects, background noises, and even full-fledged dialogues between characters.

Users can give Veo 3 a request with a description of characters and environment, as well as suggest dialogues with an indication of how exactly they should sound. As noted during the press briefing by Demis Hassabis, CEO of Google DeepMind, I quote – “For the first time, we are leaving the silent era of video generation.”

I am pleasantly shocked! The uniqueness of Veo 3 lies in its ability to understand the original pixels from generated videos and automatically synchronize created sounds with them. Although tools for generating sound based on artificial intelligence are not new, it is such integration of video and audio that distinguishes Google’s development among competitors.

There are already many tools for video generation on the market from companies such as Runway, Lightricks, Genmo, Pika, Higgsfield, Kling, Luma, as well as OpenAI and Alibaba. However, the ability to automatically generate synchronized sound gives Veo 3 a serious competitive advantage.

The new technology will be available to users through the Gemini application, presumably by subscription.

It seems that Veo 3 is a full-fledged transition from a fragmented approach to media content generation, where video and audio were created separately, to an integrated model of creating full-fledged audiovisual content with synchronized sounds, dialogues, and images. Which radically simplifies the workflow of video creation. Bravo.