Google Launches Music Generation in Gemini with Lyria 3

calendar Feb 21, 2026 · 3 min read · google gemini lyria-3 deepmind music ai  ·
Share on: linkedin copy

Google Adds Music-Generation Capabilities to the Gemini App

Google announced a significant new feature for the Gemini app: music generation using Google DeepMind’s Lyria 3 model. The feature is available in beta as of Wednesday.

How It Works

Lyria 3, Google DeepMind’s latest generative music model, enables users to create 30-second tracks using only text descriptions. Users can simply describe an idea or even upload a photo, and Gemini will translate it into a high-quality track.

Example prompts include:

  • “A comical R&B slow jam about a sock finding their match”
  • “I’m feeling nostalgic. Create a track for my mother about the great times we had as kids and the memories of her home cooked plantains. Make it a fun afrobeat track with a true African vibe”

Improvements Over Previous Lyria

Lyria 3 improves on audio generation from previous Lyria models in three important ways:

  1. No need to provide your own lyrics: They’ll be generated for you based on your prompt
  2. More creative control: You have more creative control over elements like style, vocals, and tempo
  3. More realistic music: You can create more realistic and musically complex tracks

Features

  • Text to track: Describe a specific genre, mood, inside joke, or memory to create unique tracks with lyrics or instrumental audio
  • From photos and videos to track: Upload a photo or video and watch Gemini use the content to compose a track with lyrics that fit the mood perfectly

The Gemini app creates 30-second tracks with custom cover art generated by the Nano Banana model.

YouTube Integration

Creators can also explore Lyria 3 on YouTube’s Dream Track, available in the U.S. and now rolling out to YouTube creators in other countries. Lyria 3 will enhance the quality of each unique Shorts soundtrack.

AI Content Verification

All tracks generated in the Gemini app are embedded with SynthID, Google’s imperceptible watermark for identifying Google AI-generated content. Google is also broadening verification capabilities in the Gemini app to include audio, along with image and video. Users can upload a file and ask if it was generated using Google AI.

Availability

Lyria 3 is available in the Gemini app for all users 18+ in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese, with plans to expand quality and coverage of more languages. The feature is rolling out on desktop today and to the mobile app over the next several days.

Google AI Plus, Pro and Ultra subscribers will enjoy higher limits.

Responsibility

Since launching Lyria in 2023, Google has sought to develop this technology responsibly in collaboration with the music community. Music generation with Lyria 3 is designed for original expression, not for mimicking existing artists.

If your prompt names a specific artist, Gemini will take this as broad creative inspiration and create a track that shares a similar style or mood. Google also has filters in place to check outputs against existing content.

Sources

  • Google Blog - A new way to express yourself: Gemini can now create music
  • TechCrunch - Google adds music-generation capabilities to the Gemini app
  • Ars Technica - Record scratch—Google’s Lyria 3 AI music model is coming to Gemini today
  • Google DeepMind Blog - Lyria Model

This post was generated by AI using GLM-4.7

Translations: