Google has announced the integration of a music-generation feature into its Gemini application. This innovative capability is powered by DeepMind's Lyria 3 music-generation model and is currently in its beta phase.
To utilize this feature, users simply describe their desired song, and the app will generate a 30-second track complete with lyrics. For example, a user could prompt Gemini to create a "comical R&B slow jam about a sock finding its match," and the application would produce the audio along with accompanying cover art designed by Nano Banana.
Furthermore, Google has indicated that the AI-powered tool allows for the upload of a photo or video, enabling it to generate a song that aligns with the mood or theme of the provided media file.
The company highlights that Lyria 3 represents a significant advancement over previous models, capable of producing more realistic and intricate music tracks. Users are also afforded control over various elements, including style, vocals, and tempo, to further customize their creations.
In addition to its rollout within the Gemini app, Google is extending Lyria 3's capabilities to YouTube creators via the Dream Track feature. This tool assists creators in producing AI-generated tracks and, previously exclusive to U.S. YouTube creators, is now being expanded for global availability with this latest release.
Google has clarified that while direct mimicry of existing artists is not permitted, including an artist's name in a prompt will guide Gemini to create a track reflecting a similar style or mood.
In a blog post, the company affirmed, "Music generation with Lyria 3 is designed for original expression, not for mimicking existing artists. If your prompt names a specific artist, Gemini will take this as broad creative inspiration and create a track that shares a similar style or mood. We also have filters in place to check outputs against existing content."
To ensure transparency, Google confirmed that all music generated using the Lyria 3 model will incorporate a SynthID watermark, clearly identifying it as AI-generated content. The company is also implementing features within Gemini that will allow users to upload tracks and inquire whether they were AI-generated, leveraging SynthID for identification.
The music generation feature is being progressively rolled out to all Gemini users aged 18 and above worldwide, with support for multiple languages including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.
The emergence of AI-generated music has elicited diverse reactions among artists and listeners. While platforms such as YouTube and Spotify are embracing AI, securing contracts with music labels to monetize this new form of content, AI model and tooling companies simultaneously face legal challenges from the music industry concerning copyright infringement related to training data. In response, platforms like Deezer have introduced tools specifically designed to mark AI-generated music, aiming to prevent fraudulent streaming practices.
The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.