Home
Google DeepMind's Lyria 3 Sets New AI Music Generation Standard, Free for Non-Commercial Use
Google DeepMind has officially launched Lyria 3, its newest AI model for music generation. The model is now available in beta within the Gemini app and is free for global users aged 18 and over.
Lyria 3's standout feature is its versatile creative capability. Even users without musical training can easily generate music in three ways. By simply entering a natural language prompt—like "an upbeat reggae track perfect for a beach party" or "an epic electronic piece about space exploration"—the model quickly produces a complete 30-second song. This includes vocals, lyrics, and instrumental backing, all automatically aligned with the described style, mood, and rhythm.

Users can also upload photos or screenshots, whether of landscapes, portraits, or artwork. Lyria 3 analyzes the image's atmosphere and creates original music to match the scene, along with an automatically generated album cover. For short-form video creators, uploading a video clip lets the model produce custom background music that syncs perfectly with the footage's pacing and emotional tone.
Currently, Lyria 3 has two main limitations. First, all generated music is fixed at 30 seconds, which may not suit projects requiring longer compositions. Second, the model is restricted to non-commercial use; commercial music projects need alternative solutions. Google has stated that future updates will expand functionality, including support for longer music generation, more languages, and commercial licensing options.
Related article
DeepMind CEO Hassabis: I sleep six hours a day, usually feel energetic around 1 a.m.
Fortune recently featured an interview with Demis Hassabis, CEO of Google DeepMind, revealing his unconventional approach to rest and productivity. Hassabis disclosed that he sleeps very little, structuring his waking hours into two distinct work blo
OpenAI, Anthropic Vie for Market Share Despite Revenue Shortfalls
Despite recent reports suggesting OpenAI missed revenue targets, creating pressure on tech stocks this Tuesday, private AI lab investors remain resilient. Seasoned backers have confirmed they will not reduce investment despite negative media coverage
California AV Compliance: A New Era of Tickets, Geofences, and 1M Miles
Guident operates an AuveTech shuttle in South Florida, managing a four-mile route in West Palm Beach and a one-mile route in Boca Raton using its remote monitoring technology. | Credit: GuidentCalifornia is redefining the regulatory landscape for dri
Related Special Topic Recommendations
Comments (0)
0/500
Google DeepMind has officially launched Lyria 3, its newest AI model for music generation. The model is now available in beta within the Gemini app and is free for global users aged 18 and over.
Lyria 3's standout feature is its versatile creative capability. Even users without musical training can easily generate music in three ways. By simply entering a natural language prompt—like "an upbeat reggae track perfect for a beach party" or "an epic electronic piece about space exploration"—the model quickly produces a complete 30-second song. This includes vocals, lyrics, and instrumental backing, all automatically aligned with the described style, mood, and rhythm.

Users can also upload photos or screenshots, whether of landscapes, portraits, or artwork. Lyria 3 analyzes the image's atmosphere and creates original music to match the scene, along with an automatically generated album cover. For short-form video creators, uploading a video clip lets the model produce custom background music that syncs perfectly with the footage's pacing and emotional tone.
Currently, Lyria 3 has two main limitations. First, all generated music is fixed at 30 seconds, which may not suit projects requiring longer compositions. Second, the model is restricted to non-commercial use; commercial music projects need alternative solutions. Google has stated that future updates will expand functionality, including support for longer music generation, more languages, and commercial licensing options.
DeepMind CEO Hassabis: I sleep six hours a day, usually feel energetic around 1 a.m.
Fortune recently featured an interview with Demis Hassabis, CEO of Google DeepMind, revealing his unconventional approach to rest and productivity. Hassabis disclosed that he sleeps very little, structuring his waking hours into two distinct work blo
OpenAI, Anthropic Vie for Market Share Despite Revenue Shortfalls
Despite recent reports suggesting OpenAI missed revenue targets, creating pressure on tech stocks this Tuesday, private AI lab investors remain resilient. Seasoned backers have confirmed they will not reduce investment despite negative media coverage











