Record scratch—Google's Lyria 3 AI music model is coming to Gemini today

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

Summary

Google is integrating AI-generated music capabilities into its Gemini app, utilizing the Lyria 3 model. This development follows existing AI music generators like Udio, which produce "real-sounding" but often overproduced tracks, leading to an influx of AI artists on streaming services. Google's Lyria 3 will embed an audio version of SynthID watermarking, allowing users to verify if a track was AI-generated by uploading it to Gemini. The company states it has designed Lyria 3 to respect copyright, aiming to use artist names in prompts as "broad creative inspiration" rather than direct imitation. However, Google acknowledges this process is not foolproof and encourages users to report problematic content. Lyria 3 is launching in the Gemini web interface immediately and will be available in the mobile app shortly, supporting eight languages initially, with higher usage limits for AI Pro and AI Ultra subscribers.

Key takeaway

For product managers evaluating AI content generation tools, Google's integration of Lyria 3 into Gemini, complete with SynthID watermarking and copyright-aware training, sets a new standard for responsible deployment. You should prioritize tools that offer clear provenance and mechanisms for user feedback to mitigate risks associated with AI-generated media, especially concerning intellectual property and authenticity.

Key insights

Google's Gemini app now offers AI music generation with Lyria 3, featuring SynthID watermarking and copyright considerations.

Principles

• AI-generated content requires clear provenance.
• Copyright protection is a design priority for generative AI.
• User reporting aids content moderation.

Method

Lyria 3 generates music, embedding a SynthID watermark for verification. It interprets artist names as broad creative inspiration, not direct imitation, to respect copyright.

In practice

• Upload audio to Gemini to check for SynthID watermarks.
• Report AI-generated content that imitates artists too closely.
• Utilize AI Pro/Ultra subscriptions for higher usage limits.

Topics

• AI Music Generation
• Google Gemini
• Lyria 3
• AI Watermarking
• Copyright Compliance

Best for: CTO, Executive, Product Manager, AI Product Manager, Tech Journalist, General Interest

Related on AIssential

• A new way to express yourself: Gemini can now create music — Gemini now offers AI-powered music generation via Lyria 3, complete with watermarking for content identification.
• 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.
• 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.
• 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.
• Google brings AI music to the masses — Google's Lyria 3 model integration into Gemini democratizes AI music creation for a massive consumer audience.

Open in AIssential →

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