Google's Gemini app now creates 3-minute songs with Lyria 3 Pro
Google announced Lyria 3 Pro, expanding the Gemini app's music generation capability from 30-second tracks to full 3-minute songs. The model improves structural understanding of musical composition, allowing users to prompt for specific elements like intros, verses, choruses, and bridges. Available now for Gemini subscribers with tier-based daily limits (10-50 tracks/day) and in Vertex AI, Google AI Studio, and the Gemini API for developers.
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.
Related Articles
Google DeepMind launches Lyria 3 Pro with 3-minute track generation and structural awareness
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.
Google Lyria 3 Pro extends AI music generation from 30 seconds to 3 minutes
Google has expanded its Lyria 3 music generation model to create tracks up to three minutes long—six times longer than the previous 30-second limit. The new Lyria 3 Pro adds granular control over song structure including intros, choruses, and bridges, and integrates across Google's product ecosystem including Gemini, Vertex AI, and the recently acquired ProducerAI platform.
Google TV adds Gemini visual responses, sports briefs, and deep dives
Google has launched three new Gemini-powered features for Google TV: visual responses that display live scores and tutorials, deep dives with narrated visual breakdowns on complex topics, and sports briefs offering narrated game overviews. The features are rolling out to U.S. and Canada users now, with expansion to Australia, New Zealand, and the UK planned for spring 2026.
Amazon Bedrock adds three video analysis workflows for multimodal understanding at scale
Amazon Bedrock has introduced three distinct video analysis workflows that leverage multimodal foundation models to extract insights from video content at scale. The approaches—frame-based, shot-based, and multimodal embedding—are designed for different use cases and cost-performance trade-offs, with open-source reference implementations available on GitHub.
Comments
Loading...