Google's Gemini App Now Generates 3-Minute Songs with Lyria 3 Pro

Google announced Lyria 3 Pro today, expanding its music generation capabilities in the Gemini app. The model creates complete 3-minute songs, up from the 30-second tracks available with the previous Lyria 3 model introduced last month.

Key Capabilities

Lyria 3 Pro improves structural understanding of musical composition, enabling users to specify discrete song elements. According to Google, the model now supports prompts for "specific elements like intros, verses, choruses, and bridges," providing greater creative control over generated output.

The model was trained using materials where "YouTube and Google has a right to use under our terms of service, partner agreements, and applicable law." Google confirmed the model cannot mimic specific artists—when a prompt names a creator, the system treats it as "broad inspiration" rather than imitation instruction.

Availability and Pricing

Lyria 3 Pro is now available in the Gemini app for three subscription tiers:

• Google AI Plus: 10 tracks/day
• Google AI Pro: 20 tracks/day
• Google AI Ultra: 50 tracks/day

Users access the feature by selecting "Create music" in the Tools menu. The model is also rolling out to Google Vids for Workspace customers and Google AI Pro/Ultra subscribers "starting this week" to add custom background music to creative and marketing projects.

Developer and Enterprise Access

Google is making Lyria 3 Pro available through multiple developer platforms:

Vertex AI: Now in public preview for businesses requiring on-demand audio generation at scale. Google positions this for use cases including gaming soundtrack generation and integration into creative tools, music platforms, and video editors.

Google AI Studio and Gemini API: Developers can access Lyria 3 Pro (alongside the existing Lyria RealTime model) to build music generation into custom applications.

ProducerAI: Google's collaborative music creation tool, built by musicians, now integrates Lyria 3 Pro as an "agentic experience" designed for artists, producers, and songwriters at all levels. Available globally to free and paid ProducerAI subscribers.

Safety and Content Authentication

All Lyria 3 Pro generations include SynthID watermarks for audio authentication. Google has implemented filters to "check outputs against existing content," addressing potential copyright concerns. The company did not disclose pricing for enterprise Vertex AI access or API consumption rates.

What This Means

Lyria 3 Pro extends Google's position in generative audio, directly competing with OpenAI's Suno and other music generation platforms. The 3-minute limitation and structural composition controls suggest this targets creators working on background music and branded content rather than professional music production. The availability across consumer (Gemini), enterprise (Vertex AI), and developer (API) channels indicates Google is betting on widespread adoption across multiple use cases. The emphasis on training transparency and anti-mimicry measures reflects ongoing legal and ethical scrutiny in generative audio.