Google launches 'Veo 3' to let users incorporate audio: Details inside

'Veo 3' excels from text and image prompting to real-world physics and accurate lip-syncing

Google launches Veo 3 to let users incorporate audio: Details inside
Google launches Veo 3 to let users incorporate audio: Details inside

Google has officially announced "Veo 3," an artificial intelligence (AI) video generator, which can now also create and incorporate audio.

Alphabet-owned tech giant revealed that the AI tool competes with OpenAI’s Sora video generator, but it has advanced ability to incorporate audio into the video that it creates is a key distinction.

To note, Veo 3 can incorporate audio that includes dialogue between characters along with animal sounds.

In a blog post, Google DeepMind Product Vice President Eli Collins stated, “Veo 3 excels from text and image prompting to real-world physics and accurate lip-syncing.”

Veo 3 availability

Notably, the video-audio AI tool is available to US subscribers of Google’s new $249.99 per month Ultra subscription plan.

Moreover, Veo 3 will be available for users of Google’s Vertex AI enterprise platform.

Google also launched Imagen 4, its latest image-generation tool, which produces higher-quality images through user prompts.

Users can access the tool through Gemini, Whisk, Vertex AI and Workspace.

On the other hand, the Mountain View-based tech giant updated its Veo 2 video generator to include the ability for users to add or remove objects from videos with text prompts.

Additionally, Google opened its Lyria 2 music-generation model to creators through its YouTube Shorts platform and businesses using Vertex AI.

It is worth noting that the launch of Veo 3 marks a significant advancement in AI-driven video production, where both imagery and audio are developed in seamless unison.