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

Post Thumbnail

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.

AIvengo > Reviews > Revolution in content creation: Veo 3 generates dialogues and sound effects
Почитать из последнего
UBTech will send Walker S2 robots to serve on China's border for $37 million
Chinese company UBTech won a contract for $37 million. And will send humanoid robots Walker S2 to serve on China's border with Vietnam. South China Morning Post reports that the robots will interact with tourists and staff, perform logistics operations, inspect cargo and patrol the area. And characteristically — they can independently change their battery.
Anthropic accidentally revealed an internal document about Claude's "soul"
Anthropic accidentally revealed the "soul" of artificial intelligence to a user. And this is not a metaphor. This is a quite specific internal document.
Jensen Huang ordered Nvidia employees to use AI everywhere
Jensen Huang announced total mobilization under the banner of artificial intelligence inside Nvidia. And this is no longer a recommendation. This is a requirement.
AI chatbots generate content that exacerbates eating disorders
A joint study by Stanford University and the Center for Democracy and Technology showed a disturbing picture. Chatbots with artificial intelligence pose a serious risk to people with eating disorders. Scientists warn that neural networks hand out harmful advice about diets. They suggest ways to hide the disorder and generate "inspiring weight loss content" that worsens the problem.
OpenAGI released the Lux model that overtakes Google and OpenAI
Startup OpenAGI released the Lux model for computer control and claims this is a breakthrough. According to benchmarks, the model overtakes analogues from Google, OpenAI and Anthropic by a whole generation. Moreover, it works faster. About 1 second per step instead of 3 seconds for competitors. And 10 times cheaper in cost per processing 1 token.