Google’s Gemini App Now Lets Users Create AI-Generated Music with Lyria 3
San Francisco, CA – Google’s Gemini application is now equipped with Lyria 3, a latest artificial intelligence model capable of generating 30-second custom soundtracks from text or image prompts. This development, announced on February 18, 2026, marks a significant step in democratizing music creation, allowing users with no formal musical training to produce original audio tracks. The integration of Lyria 3 into Gemini opens up possibilities for personalized content creation, from unique social media posts to customized background music for presentations and projects. The technology is currently available in eight languages and is aimed at users aged 18 and over.
The ability to generate music directly within Gemini is powered by Lyria 3, Google’s most advanced music generation model to date. Unlike previous AI music tools that often required users to provide lyrics, Lyria 3 can autonomously generate both lyrics and instrumentals based on a given prompt. This simplifies the creative process, making it accessible to a wider audience. The system also offers users greater control over the style, vocals, and tempo of the generated music, allowing for a more tailored output. According to Google, Lyria 3 is designed to create “realistic and musically complex tracks,” moving beyond simple melodies to produce more sophisticated compositions.
How Lyria 3 Works: From Prompt to Soundtrack
The process of creating music with Lyria 3 is remarkably straightforward. Users simply input a text prompt describing the desired mood, genre, or theme of the track. Alternatively, they can upload an image, and the AI will interpret the visual content to generate a corresponding soundtrack. For example, a user could prompt Gemini with “a relaxing beach scene” or “upbeat music for a workout video,” and Lyria 3 will generate a 30-second track designed to match that description. The model can produce a wide range of musical styles, including jazz, disco, hip-hop, and electronic music, as demonstrated by examples showcased by Google. The generated tracks also include custom cover art created by another Google AI model, Nano Banana.
The versatility of Lyria 3 extends beyond simple prompts. Users can refine their requests by specifying desired vocals, tempos, and musical styles. This level of control allows for a more nuanced and personalized musical experience. The model’s ability to generate lyrics automatically eliminates a common barrier to entry for aspiring musicians, while its capacity to create complex arrangements suggests a significant advancement in AI-powered music generation. The technology is designed to be intuitive and user-friendly, making it accessible to individuals with varying levels of technical expertise.
Availability and Access
Lyria 3 music generation within Gemini is currently available globally in English, Japanese, Korean, Hindi, Spanish, Portuguese, German, and French. Access is restricted to users over the age of 18. For Google Workspace customers and Workspace Individual subscribers, access to the Gemini app – and therefore Lyria 3 – is controlled through the Generative AI settings in the Workspace Admin console. Google’s Workspace Admin Help Center provides detailed information on managing these settings. End users who already have access to the Gemini app will automatically receive access to Lyria 3. To begin creating music, users simply select the “Create music” option from the tools menu within the Gemini app.
The rollout of this feature is proceeding in two phases: Rapid Release and Scheduled Release domains. As of February 18, 2026, the feature is fully rolled out to both types of domains, with visibility expected within 1-3 days for all eligible users. This phased approach allows Google to monitor performance and address any potential issues before widespread adoption. The company has also provided resources, including blog posts and help center articles, to assist users in getting started with Lyria 3.
Beyond Simple “Bangers”: The Potential of AI Music Generation
While some early reactions have playfully referred to the generated tracks as “bangers,” the potential applications of Lyria 3 extend far beyond creating short, catchy tunes. The technology offers a powerful tool for educators, allowing them to generate custom instrumentals for classroom presentations or student projects. Businesses can use it to create unique soundtracks for marketing materials or internal communications. Individuals can personalize their social media content or simply explore their creativity through music. The ability to quickly and easily generate original music has the potential to transform the way we create and consume audio content.
The development of Lyria 3 represents a broader trend in the field of artificial intelligence, where AI models are increasingly capable of generating creative content. From writing articles and creating images to composing music, AI is becoming a valuable tool for artists, educators, and businesses alike. As these models continue to evolve, we can expect to observe even more innovative applications emerge, further blurring the lines between human and artificial creativity. The ease of use and accessibility of Lyria 3 within the Gemini app positions Google at the forefront of this rapidly evolving landscape.
Key Takeaways
- AI-Powered Music Creation: Lyria 3 in Gemini allows users to generate 30-second custom soundtracks from text or image prompts.
- Accessibility and Control: The tool is designed to be user-friendly and offers control over style, vocals, and tempo.
- Global Availability: Currently available in eight languages to users 18 and older.
- Versatile Applications: Potential uses range from educational materials to personalized social media content.
Google plans to continue refining Lyria 3 based on user feedback and technological advancements. The company has not yet announced any specific plans for future updates, but it is likely that we will see further improvements in the quality, complexity, and customization options of the generated music. Users can expect ongoing development and integration of AI-powered creative tools within the Gemini ecosystem. The next update regarding Gemini’s AI capabilities is expected during Google I/O in May 2026.
What are your thoughts on AI-generated music? Share your experiences and ideas in the comments below, and don’t forget to share this article with your network!
