A new way to express yourself: Gemini can now create music

2026-02-18 · Source: AI · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Emerging Technologies & Innovation · Depth: Fundamental Awareness, medium

Summary

The Gemini app now integrates Google DeepMind's Lyria 3, an advanced music generation model, enabling users to create 30-second audio tracks with custom cover art from text descriptions or uploaded images. This beta feature, available to users 18+ in multiple languages, enhances previous Lyria models by generating lyrics, offering greater creative control over style and tempo, and producing more complex, realistic tracks. All music generated within the Gemini app is embedded with SynthID, an imperceptible watermark, allowing for verification of AI-generated content. Google emphasizes responsible AI development, incorporating copyright considerations, content filters, and user policies to prevent intellectual property violations and mimicry of existing artists.

Key takeaway

For AI Product Managers evaluating new creative tools, consider how Gemini's Lyria 3 integration demonstrates a balanced approach to generative AI. Your teams should explore its capabilities for rapid content creation, noting the embedded SynthID watermarking as a crucial feature for transparency and responsible deployment. This model offers a blueprint for integrating advanced AI while addressing ethical concerns like copyright and content identification.

Key insights

Gemini now offers AI-powered music generation via Lyria 3, complete with watermarking for content identification.

Principles

• AI-generated content requires clear identification.
• Creative control enhances user expression.
• Responsible AI development includes copyright safeguards.

Method

Users describe an idea or upload a photo to the Gemini app, which then employs Lyria 3 to generate a 30-second music track with lyrics and custom cover art.

In practice

• Generate unique soundtracks for social media Shorts.
• Create personalized music for gifts or memories.
• Verify audio authenticity using SynthID.

Topics

• Music Generation
• Generative AI
• Google Gemini
• Lyria 3
• SynthID

Best for: AI Product Manager, Creative Technologist, AI Chatbot Developer, General Interest

Related on AIssential

• Record scratch—Google's Lyria 3 AI music model is coming to Gemini today — Google's Gemini app now offers AI music generation with Lyria 3, featuring SynthID watermarking and copyright considerations.
• Google adds AI music generation to Gemini with Lyria 3 — Google's Lyria 3 model enables AI music generation in Gemini and YouTube, featuring mood-matching and content identification.
• Build with Lyria 3, our newest music generation model — Lyria 3 offers AI music generation with structural coherence, expressive vocals, and granular control via text and multimodal inputs.
• Google Gemini Integrates AI Music Generation — Google's Lyria 3 model integrates AI music generation into Gemini and YouTube, offering creative tools with guardrails.
• 😺 Watch: This AI just made our podcast theme song — Google's Flow Music, powered by Lyria 3, enables iterative AI-driven music and video creation.
• Google launches AI music generator Lyria 3 Pro, says it was trained on data it has the right to use — Google's Lyria 3 Pro advances AI music generation with improved structural understanding and broad platform integration.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by AI.