Google announced the integration of its most advanced AI music generation model, Lyria 3, into the Gemini app, with global rollout starting February 19th. Developed by Google DeepMind, this latest version of the Lyria series represents a significant upgrade from previous tools that could only generate instrumental music to a system capable of creating complete songs.
Lyria 3 can not only automatically compose music, but also simultaneously generate original lyrics and more realistic vocal effects. Users can freely set the style, mood, rhythm, and singing style, and even adjust the instrument configuration to make the creation closer to their imagination. This means that from inspiration to finished product, there is no longer a need for complicated music production processes.
A 30-second high-quality song, starting with a prompt word.
With Gemini, users simply need to access the "Create music" function, enter a description of the desired song, and the system will generate a 30-second high-fidelity music track. Whether it's high-energy rock, laid-back lo-fi, or a humorous advertising jingle, it can all be created with simple prompts.
Google showcased examples including a high-energy 90s skateboard punk track with lyrics complaining about a roommate not doing the dishes, accompanied by fast drumbeats and male vocals; lo-fi music inspired by sunset photos; and cinematic soundtracks generated from video content. These examples demonstrate Lyria 3's ability to understand context and atmosphere, making music creation intuitive and fun.
Automatically generates covers and includes a built-in watermark, balancing creativity and responsibility.
In addition to the music itself, Gemini also creates a unique cover art for each generated song. The cover art is generated by Google's Nano Banana image model, giving the work a more complete feel when shared. Users can directly download the music and cover art for use in social media posts, short videos, or personal projects.
As AI-generated content rapidly becomes more widespread, Google also emphasizes the importance of accountability mechanisms. Every song generated through Lyria 3 is embedded with an invisible SynthID digital watermark to identify whether it is AI-generated content. Users can even upload audio files for verification to confirm the presence of this marker, demonstrating Google's proactive efforts to ensure the verifiability of AI-generated music.
Globally available, subscribers enjoy higher quotas
Lyria 3 is currently available on the desktop version of Gemini and will be gradually expanded to mobile devices. It is available to users worldwide aged 18 and over and supports eight languages: English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.
Regarding usage limitations, free users can generate approximately 10 songs per day, while Gemini AI Plus, Pro, and Ultra subscribers have a higher generation limit. This design allows for easy access for general users while providing greater creative freedom for hardcore creators.
Social media buzz and YouTube expansion: AI music is gaining widespread acceptance.
After its launch, Lyria 3 quickly sparked a wave of discussion on X (formerly Twitter). Many users shared their own meme songs, K-pop experimental tracks, and even custom theme songs for their daily lives. This instant generation and low barrier to entry for creation is attracting a large number of content creators and amateur music enthusiasts to give it a try.
At the same time, Google also announced that YouTube's Dream Track feature is now available globally, allowing creators to use technology similar to Lyria to generate AI music clips, further expanding the possibilities of audio-visual creation.
Gemini transforms into a comprehensive AI creation platform
With the addition of Lyria 3, Gemini is no longer just a text or image tool, but a multimedia creation platform encompassing text, images, videos, and music. The line between AI and professional creative software is gradually blurring, and the barrier to creation is being significantly lowered.
When a melody can be generated instantly from just a few words, everyone could potentially have their own original theme song. Google encourages users to continue experimenting and sharing; perhaps, an AI-driven era of personal music has officially begun.
This article, "Google Launches Lyria 3: Gemini Generates Your Own AI Song with One Click, Handling Everything from Lyrics to Vocals," first appeared on ABMedia, a ABMedia .
