Editorial illustration for Google adds AI music creation to Gemini with Lyria 3.5
Google Adds AI Music Generation to Gemini
Google added a music generation model called Lyria 3.5 to the Gemini app on Tuesday, letting users type a prompt and get back a finished song rather than just an image or a paragraph of text. The model also ships through the API, giving developers a way to build it into their own products.
Inside Gemini, the tool lets people pick a genre and style, decide whether they want vocals or instrumentals, and set the length of the track. Google built in templates aimed at first-time users, including options for background music and personalized birthday songs, so people don't have to start from a blank prompt.
Lyria 3.5 isn't confined to Gemini. Google has also folded it into Flow Music, where it comes with extra features, into AI Studio for developers who want more control, and into Google Vids for anyone scoring a video project. That spread across four separate products suggests Google sees music generation as a feature it wants everywhere, not a standalone experiment.
The bigger question, as with any generative model, is what it was actually trained on.
Google releases its Lyria 3.5 music generation model in the Gemini app and via API. According to Google, Lyria 3.5 delivers more expressive vocals and richer musical arrangements than its predecessor.
Why this matters
Google folding Lyria 3.5 straight into Gemini, rather than keeping it siloed in a separate creative tool, tells us where the company thinks music generation actually needs to live: next to the assistant people already open dozens of times a day. That distribution move matters more than the vocal quality claims. For developers, the API access alongside Google Flow means Lyria 3.5 becomes another building block to wire into apps, not just a consumer novelty for birthday songs.
For founders building in audio or content tools, this is a reminder that the model layer keeps getting absorbed into platform giants faster than standalone startups can differentiate on quality alone. Worth watching: how Google licenses this for commercial use, since "personalized birthday songs" and background-music templates suggest a UGC and small-business angle rather than pro production. We'd also want independent listening tests before taking Google's own comparison to the prior Lyria version at face value.
The real signal will be adoption inside Flow and third-party apps over the next few months.
Related Reading
Browse all Google news →
LLMs & Generative AI ChatGPT's 'Nerdy' tweak rewards goblin metaphors in answers, study finds
LLMs & Generative AI Google tests visual 'magazine-style' UI for Gemini 3 Pro users
LLMs & Generative AI AI Engineers Face Rising Costs, Need New Strategies for Efficiency
Related Topic NVIDIA and Google Cloud let developers scale AI from prototype to production
Market Trends
Related Topic Google's FACTS benchmark shows 70% factuality ceiling across four tests
Research & Benchmarks
From Archives Seattle Times, Newsday Sue OpenAI and Microsoft
From Archives Study: Chatbots Beat Fact Sheets at Reducing Conspiracy Beliefs
From Archives Google DeepMind's WeatherNext 3 Uses Station Data for Hourly 5 km Forecasts
Research & Benchmarks
From Archives Google's Gemini Flash Models Cut Video Tokens by 88% With Agentic Processing
Business & Startups
Common Questions Answered
How does Lyria 3.5 differ from previous versions of Google's music generation model?
Lyria 3.5 delivers more expressive vocals and richer musical arrangements compared to its predecessor. These improvements make the generated music sound more natural and sophisticated than earlier iterations of the model.
What customization options are available when creating music with Lyria 3.5 in Gemini?
Users can select a specific genre and style, choose whether they want vocals or instrumental tracks, and set the desired length of the song. The tool also includes templates designed to help first-time users get started with music creation.
How can developers integrate Lyria 3.5 into their own applications?
Google provides API access to Lyria 3.5, allowing developers to build the music generation capability directly into their own products. This API integration makes Lyria 3.5 a reusable building block rather than just a consumer-facing feature.
Why is Google integrating Lyria 3.5 directly into Gemini instead of keeping it as a separate tool?
By embedding music generation into Gemini, Google is positioning the feature next to an assistant that users already open dozens of times daily, making it more accessible and integrated into users' workflows. This distribution strategy prioritizes reaching users where they already spend time rather than requiring them to switch to a specialized tool.
Further Reading
- Create your best tracks yet with Lyria 3.5 in Gemini - Google Blog
- Google adds music-generation capabilities to the Gemini app - TechCrunch
- Gemini can now generate AI music for you, no lyrics required - Ars Technica
- Gemini hands Lyria 3.5 the mic as the music model makes its debut on the app - Android Authority
- Google brings its Lyria 3.5 music model to every Gemini user - The Next Web
