Google has announced its newest generative media models, which mark significant breakthroughs in creating breathtaking images, videos, and music that empower artists to bring their creative vision to life. These models are designed to give everyone the tools to express themselves.
The new models include Veo 3, a state-of-the-art video generation model that can create videos with audio, and Imagen 4, which combines speed with precision to create stunning images. Lyria 2, a powerful composition and exploration tool, is now available for creators through YouTube Shorts and enterprises in Vertex AI.
Flow, an AI filmmaking tool designed for Veo, lets users seamlessly create cinematic clips, scenes, and stories by bringing together Google DeepMind’s most advanced models: Veo, Imagen, and Gemini. The new models are the result of close partnership with the creative industries to shape them responsibly and give creators new tools to realize the possibilities of AI in their art.
Veo 3 can generate videos with audio, traffic noises, birds singing, or dialogue between characters, and excels from text and image prompting to real-world physics and accurate lip syncing. The model is available today for Ultra subscribers in the United States in the Gemini app and in Flow. It’s also available for enterprise users on Vertex AI.
Imagen 4 has remarkable clarity in fine details, excelling in photorealistic and abstract styles, and can create images in a range of aspect ratios up to 2k resolution. The fast variant of Imagen 4 is coming soon.
Lyria 2 brings powerful composition and endless exploration, empowering musicians, producers, and songwriters with experimental tools that spark new creative possibilities. Lyria RealTime allows anyone to interactively create, control, and perform generative music in real time.
SynthID Detector, a verification portal, helps people identify AI-generated content by uploading a piece of content and verifying if it has SynthID watermark. The models will continue to have SynthID watermarks, ensuring responsible creation and collaboration with the creative community.
Source: https://blog.google/technology/ai/generative-media-models-io-2025