product updateGoogle DeepMind

Google DeepMind launches Lyria 3 Pro with 3-minute track generation and structural awareness

TL;DR

Google DeepMind introduced Lyria 3 Pro, an advanced music generation model capable of creating tracks up to 3 minutes long with structural awareness of musical composition elements like intros, verses, choruses, and bridges. The model is rolling out across multiple Google products including Vertex AI, Google Vids, Gemini app, and the new ProducerAI collaborative tool.

2 min read
0

Google DeepMind Launches Lyria 3 Pro with Extended Track Generation

Google DeepMind released Lyria 3 Pro, its most advanced music generation model to date, capable of creating tracks up to 3 minutes long with enhanced structural awareness of musical composition.

Key Capabilities

Lyria 3 Pro introduces structural awareness, enabling users to prompt for specific musical elements including intros, verses, choruses, and bridges. The model supports complex transitions and style experimentation, addressing previous limitations in musical coherence.

The system generates music using training materials from YouTube and Google's existing rights and partner agreements. All outputs are embedded with SynthID, Google's imperceptible watermark for identifying AI-generated content.

Rollout Across Google Products

Vertex AI: Now in public preview for enterprises requiring on-demand audio at scale, enabling organizations to generate bespoke soundtracks for gaming, creative tools, music, and video platforms.

Google AI Studio and Gemini API: Developers can access Lyria 3 Pro alongside Lyria RealTime, providing improved musical awareness and structural coherence for creative tool development.

Google Vids: Rolling out to Google Workspace customers and Google AI Pro & Ultra subscribers starting the week of March 25, 2026. Users can add custom music matching their style for creative projects and marketing videos.

Gemini app: Longer generations with Lyria 3 Pro available to paid subscribers, enabling creation of personalized tracks for vlogs, podcasts, and tutorial videos.

ProducerAI: Google's new collaborative music creation tool, built with musician input, offers an agentic experience for artists, producers, and songwriters to iterate on comprehensive songs. Available globally to free and paid subscribers.

Responsible Development

Google developed Lyria 3 Pro in partnership with the music industry through its Music AI Sandbox, which provides experimental tools to musicians, producers, and songwriters. The model does not mimic specific artists—when prompts name creators, the system treats the reference as broad stylistic inspiration.

Google implemented filters to check outputs against existing content. Users must comply with Terms of Service and Gen AI prohibited use policies, which prohibit intellectual property and privacy violations. Grammy-winning producer Yung Spielburg and DJ/producer François K collaborated with Google during development, using Lyria in their composition processes.

What This Means

Lyria 3 Pro significantly extends Google's music generation capabilities beyond its predecessors by adding both duration (3 minutes versus prior limitations) and structural understanding. The multi-product rollout signals Google's strategy to distribute music AI across its developer platforms, consumer products, and enterprise tools simultaneously. The emphasis on responsible development and SynthID watermarking reflects ongoing industry tension around AI-generated content and artist attribution, though the approach of treating specific artist names as style inspiration rather than direct mimicry represents a technical choice rather than a legal safeguard.

Related Articles

product update

Google Expands Gemini-Powered Ask Maps Globally With Personal Intelligence, Real-Time Transit, Agentic Ordering

Google Maps' Gemini-powered Ask Maps chat is rolling out globally to English speakers in Australia, Brazil, Canada, Indonesia, Japan, Mexico, and over 150 other countries and territories. The update adds Gmail-based Personal Intelligence, real-time transit data, conversation memory, and agentic capabilities for ordering food and booking hotels.

product update

Anthropic Adds Cross-Session Messaging to Claude Code v2.1.224

Claude Code v2.1.224 introduces cross-session messaging, letting separate Claude Code instances on macOS and Linux send each other summaries to coordinate work. The feature does not support approving permissions or executing commands remotely.

product update

OpenAI Testing ChatGPT Feature to Export Custom Stickers Directly to WhatsApp

An APK teardown of ChatGPT's Android app reveals a hidden 'ChatGPT Stickers' feature that would let users create custom stickers and export them directly into WhatsApp as sticker packs. The feature is unreleased and its public launch timeline is unknown.

product update

Anthropic Sets Claude Code Auto Mode as Default Starting August 14

Anthropic will switch Claude Code's default permission setting to auto mode on August 14 for Pro, Max, and Team users. The company says its safety classifier caught 89% of dangerous commands in testing, compared to 13.6% for human reviewers, and will no longer charge extra tokens for the classifier itself.

Comments

Loading...