Editorial illustration for Google adds Lyria 3 text‑to‑music to Gemini, enabling song creation via prompts
Lyria AI: Generate Music with Text Prompts Now
Google adds Lyria 3 text‑to‑music to Gemini, enabling song creation via prompts
Google has woven its newest audio model into the Gemini app, turning a chat‑based interface into a makeshift studio. The addition marks a shift from the platform’s text‑only roots toward a broader creative toolbox that now includes melody and lyric generation. Users will be able to type a description—whether it’s a genre, a feeling, or a personal memory—and receive a custom track in return.
This capability sits alongside Gemini’s existing language and image features, suggesting Google’s intent to bundle multiple generative modes under a single umbrella. While the technical details remain sparse, the rollout hints at a more seamless way for everyday people to experiment with music without any prior training. The move also raises questions about how such tools will be used, from personal projects to commercial content.
Below, the company’s own description of what the feature can do illustrates the practical promise of prompting a song from a single line of text.
Lyria 3's text-to-music capabilities allow Gemini app users to make songs by describing specific genres, moods, or memories, such as asking for an "Afrobeat track for my mother about the great times we had growing up." The music generator can make instrumental audio and songs with lyrics composed automatically based on user prompts. Users can also upload photographs and video references, which Gemini then uses to generate a track with lyrics that fit the vibe. "The goal of these tracks isn't to create a musical masterpiece, but rather to give you a fun, unique way to express yourself," Google said in its announcement blog.
Will users find the 30‑second snippets useful? The Gemini app now hosts DeepMind’s Lyria 3 model, letting anyone type a genre, mood or memory and receive a short track without leaving the chat window. Short, instrumental loops or full‑song verses with lyrics can be produced in response to text, images or video prompts, as the rollout reaches beta participants.
Yet the offering is confined to thirty‑second excerpts, which may limit creative depth and practical application. Because the music is generated on‑the‑fly, it's unclear whether the quality matches that of human‑composed pieces or how well it adapts to more complex requests. The integration demonstrates Google’s push to embed generative audio alongside text and visual capabilities, but the real test will be user adoption and the model’s ability to handle diverse cultural styles beyond the examples cited.
For now, the feature remains a preview, and its impact on broader music‑creation workflows is still uncertain.
Further Reading
Related Reading
Browse all Google news →
LLMs & Generative AI Ant Group unveils Ring-1T, first open-source trillion-parameter reasoning model
LLMs & Generative AI ChatGPT Health Event Shows AI Modernizing Dev Workflows, GitLab Unveils Plans
LLMs & Generative AI Gen AI app sessions up fivefold, downloads jump 778% as ChatGPT leads traffic
Related Topic Google AI Advisors Let Users Probe Performance with Conversational “Why” Queries
Research & Benchmarks
Related Topic Google.org launches USD 30 M AI for Government Innovation Impact Challenge
Research & Benchmarks
From Archives Gemini app expands tools, now generates music alongside images and video
From Archives Graphite blends stacked PRs with AI analysis for faster, higher-quality reviews
From Archives Google Sets Dates for I/O 2026, Promises Keynotes, Demos and Fireside Chats
Business & Startups
From Archives Google's AI search results add hover pop‑up links in Overviews and AI Mode
AI Tools & Apps
Common Questions Answered
How does Lyria generate music through the Gemini API?
Lyria generates instrumental music by converting text prompts into audio tracks using a sophisticated music tokenizer and decoder that tracks timing, key centers, and timbre. [techsith.com](https://techsith.com/can-gemini-create-music/) notes that the system can create short clips with live steering, allowing users to modify tempo, key, and arrangement in near real-time.
What are the key limitations of Lyria's music generation capabilities?
[docs.cloud.google.com](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/music/generate-music) indicates that Lyria has several important limitations, including generating only instrumental music and producing audio clips with a maximum length of 32.8 seconds. The system currently supports only US English prompts and applies safety filters to prevent the creation of inappropriate or offensive content.
What elements should be considered when creating a Lyria music generation prompt?
[docs.cloud.google.com](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/music/music-gen-prompt-guide) recommends including several key elements in your prompt, such as production quality, soundscape/ambiance, arrangement/structure, tempo & rhythm, instrumentation, mood & emotion, and genre & style. A good prompt is descriptive and clear, starting with a core musical idea and then refining it by adding specific keywords and modifiers.