Google has integrated AI-generated music capabilities into its Gemini chatbot, powered by DeepMind's latest audio model, Lyria 3. Beta access to Lyria 3 is currently rolling out within the Gemini app, enabling users to create 30-second music tracks directly from text descriptions, images, or videos, all without exiting the chatbot interface.
This innovative music-making tool is now globally available in multiple languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese, with future expansion plans. Access is restricted to Gemini app users who are 18 years of age or older.
Lyria 3’s text-to-music functionality allows Gemini app users to compose songs by articulating specific genres, moods, or personal memories. For instance, a user could request an “Afrobeat track for my mother about the great times we had growing up.” The generator can produce both instrumental audio and songs with automatically composed lyrics based on user prompts. Additionally, users can upload photographs and video clips, which Gemini then interprets to generate a corresponding track with lyrics that capture the intended ambiance.
Google clarified its objective in its announcement blog, stating, “The goal of these tracks isn’t to create a musical masterpiece, but rather to give you a fun, unique way to express yourself.”
To enhance the user experience, Gemini will automatically append custom cover art, generated by Nano Banana, to the created songs, facilitating easier sharing and downloading. Google is also extending Lyria 3's capabilities to YouTube’s Dream Track tool, empowering creators to generate bespoke AI soundtracks for their Shorts content.
While Dream Track and Lyria were initially demonstrated with the ability to emulate the style and voice of renowned performers, Google emphasizes its commitment to copyright in Lyria 3’s development. The company states that the tool “is designed for original expression, not for mimicking existing artists.” When prompted for a specific artist, Gemini will instead generate a track that “shares a similar style or mood” and employs filters to cross-reference outputs against existing copyrighted material.
Lyria has been in existence since 2023, though its access was previously confined to Google Cloud’s Vertex platform. This expansion to the Gemini app significantly broadens Lyria's accessibility, albeit arriving after platforms such as TikTok and Microsoft’s Copilot have already introduced their own AI music creation tools.
The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.