Google launches Lyria 3 Pro music generation model, capable of creating tracks up to 3 minutes long

Google launches Lyria 3 Pro music generation model, capable of creating tracks up to 3 minutes long

```

Google has significantly upgraded its AI music generation capabilities with the launch of the Lyria 3 Pro music generation model, which can create tracks up to three minutes long.

On Wednesday, March 25, Google announced the launch of the Lyria 3 Pro music generation model, just one month after the previous generation, Lyria 3, was released.

The new model dramatically increases the maximum duration of a single generated track from 30 seconds to 3 minutes, and also supports fine customization of musical structural elements.

Lyria 3 Pro will simultaneously launch on the Gemini application (paid users only), the video creation tool Google Vids, the AI music production platform ProducerAI, as well as business products such as Vertex AI, Gemini API, and AI Studio, covering multiple core scenarios from consumer to enterprise levels.

This series of deployments shows that Google is accelerating the integration of AI music capabilities into its product ecosystem and seeking to open up new revenue streams in the enterprise market.

Core Upgrades: From Fragments to Complete Tracks

Compared with Lyria 3, the most significant changes in Lyria 3 Pro are in generation duration and structural awareness.

The new model supports the creation of tracks up to 3 minutes long, and can identify and generate specific musical structural elements, including intros, verses, choruses, and transitions. This means users can specify a complete song structure directly in prompts, rather than just describing style or mood.

According to Google, Lyria 3 Pro is particularly suitable for creative scenarios that require complex transitions between sections or want to experiment with multiple styles, providing a more complete solution for content creators such as podcast soundtracks, vlog background music, and instructional videos.

Google is attempting to enhance the credibility of the Lyria product line within creative communities through collaborations with professional musicians.

Grammy-winning producer Yung Spielburg has already used Lyria for soundtrack creation and production in Google DeepMind shorts.

DJ and producer François K has used Lyria iteratively to create a new song soon to be released. Google’s Music AI Sandbox project also continues to provide experimental tools for musicians, producers, and songwriters, and the feedback has been incorporated into the development of Lyria 3.

Multi-Platform Deployment: Covering Developers, Enterprises, and Creators

This time, Google is extending Lyria 3 Pro’s reach to multiple different audience groups.

For enterprise users, Lyria 3 Pro is now in public preview on Vertex AI, supporting on-demand, large-scale generation of high-fidelity audio for scenarios such as rapid customization of game soundtracks and integration into creative tool sets.

For developers, Lyria 3 Pro is available on AI Studio alongside Lyria RealTime, and can be accessed via the Gemini API for building next-generation creative tools.

For regular users, Google’s AI video creation app Google Vids is rolling out Lyria 3 and Lyria 3 Pro features this week to Google Workspace customers and Google AI Pro/Ultra subscribers, allowing users to add custom soundtracks to creative or marketing videos.

Long-track generation features in the Gemini app are simultaneously open to paid users.

Regarding ProducerAI, Google completed its acquisition of this AI music production tool last month. After integrating Lyria 3 Pro, ProducerAI will offer an intelligent agent-style creative experience for artists, producers, and songwriters, and is now available to global free and paid users.

Amid ongoing industry concerns about the copyright of AI-generated content, Google has disclosed the model’s data sources and content identification mechanisms.

Google states that Lyria 3 Pro's training data comes from partner-authorized data as well as available data from YouTube and Google platforms.

The company emphasizes that the model does not directly imitate the style of specific artists, but if a user specifies an artist in the prompt, the model will draw ‘broad inspiration’ from that artist’s style when generating tracks.

All tracks generated by Lyria 3 and Lyria 3 Pro will be embedded with a SynthID watermark to identify their AI-generated attributes.

This measure aligns with the general trend in the industry. Reportedly, Spotify launched a new tool this week allowing artists to check songs released under their names to prevent misattributed AI-generated content. Streaming platform Deezer has also introduced a tool for any streaming service to identify AI music.

Risk Warning and DisclaimerThe market is risky; investments should be made cautiously. This article does not constitute personal investment advice and has not considered the individual investment objectives, financial situations, or needs of specific users. Users should consider whether any opinions, views, or conclusions in this article are suitable for their particular situation. Any investment based on this is at your own risk. ```