Google is expanding the creative capabilities of its Gemini app with the launch of Lyria 3, a new AI-powered music generator. The tool allows users to create 30-second musical tracks from text prompts, images, and even videos, complete with vocals and instrumentals. This marks a significant step in making AI-driven music creation accessible to a wider audience, moving beyond specialized platforms and into a mainstream application.
Lyria 3, developed by Google DeepMind, represents the company’s most advanced music generation model to date. The integration into Gemini aims to empower users to express themselves through music in novel ways, whether it’s crafting a soundtrack for a social media post, generating a jingle for a presentation, or simply exploring musical ideas. The rollout, beginning February 18, 2026, is available globally in English, Japanese, Korean, Hindi, Spanish, Portuguese, German, and French for users aged 18 and over.
Unlike previous iterations, Lyria 3 is now directly accessible within the Gemini app, eliminating the need for access through platforms like Google Cloud’s Vertex AI or limited beta programs for YouTubers. This broader availability signals Google’s confidence in the technology and its potential for widespread adoption. Users can simply select the “Create music” option within the Gemini app to begin experimenting with the tool, as detailed in a Google Workspace blog post.
How Lyria 3 Works
The process is designed to be intuitive. Users provide a text prompt describing the desired music – specifying genre, mood, or even a narrative – and Lyria 3 generates a corresponding track. Alternatively, users can upload an image or video, and the AI will create music inspired by the visual content, even generating lyrics to match the scene. Google’s “Nano Banana” model then automatically creates cover art to accompany the track. This capability mirrors the functionality of AI image generators like OpenAI’s DALL-E, but applied to the realm of audio, as noted in Times Now News.
The generated tracks are 30 seconds in length, a deliberate choice that encourages quick creation and sharing. Users can then download or share their creations directly from the Gemini app to various platforms. According to Google’s Lyria 3 overview page, the tool is designed to “make it, hear it, share it,” emphasizing its ease of use and social sharing potential.
Addressing Creative Concerns
While Google emphasizes that Lyria 3 is designed to foster “original expression” and avoid imitating existing artists, the emergence of AI music generators inevitably raises questions about copyright and the potential impact on the music industry. The source material used to train these models is a growing area of legal scrutiny, and it remains to be seen whether further legal challenges will arise regarding the use of copyrighted material in AI training datasets. The German-language publication pte.at notes this potential for legal challenges, highlighting the ongoing debate surrounding AI and artistic creation.
Administrators controlling access to the Gemini app within Google Workspace environments can manage music generation through existing Generative AI settings in the Workspace Admin console. This allows organizations to maintain control over the use of AI tools within their environments.
What’s Next for AI-Generated Music?
The launch of Lyria 3 represents a significant step forward in the democratization of music creation. As AI models continue to improve, we can expect even more sophisticated tools that empower individuals to express their creativity through music, regardless of their musical training or experience. The ongoing development of these technologies will likely continue to spark debate about the role of AI in the arts and the future of copyright law. The integration of AI music generation into widely used applications like Gemini suggests that this technology is poised to become increasingly prevalent in the coming years.
What are your thoughts on AI-generated music? Share your opinions in the comments below!
