Google has introduced a new AI-powered music generation feature inside the Gemini app, powered by DeepMind’s Lyria 3 model.
The feature is currently in beta and allows users to create original songs simply by describing what they want.
To generate music, users can enter a prompt such as a specific genre, mood, or creative theme. Gemini then produces a 30-second track complete with lyrics and AI-generated cover art. Users can also upload a photo or video, and the system will create a song that matches the mood or style of the uploaded content. According to Google, Lyria 3 improves upon earlier versions by generating more realistic, layered, and complex compositions. Users can adjust elements like tempo, vocals, and musical style.
Alongside its rollout in Gemini, Google is expanding access to Dream Track on YouTube. Previously limited to creators in the United States, the AI music tool will now be available globally, allowing creators to generate background tracks directly for their videos.
Google emphasized that the system is designed for original creation, not imitation. While users may reference an artist’s name in prompts, Gemini will only generate music inspired by a similar style or mood rather than replicating a specific artist’s sound. The company also uses filters to compare generated tracks against existing content.
All songs created using Lyria 3 will include a SynthID watermark, a technology developed by Google DeepMind to identify AI-generated content. Gemini will also allow users to upload audio files to check whether they were generated using AI.
The feature is rolling out globally to Gemini users aged 18 and older, with support for multiple languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.
If this article helped you, please consider supporting our work. Every small contribution keeps Abijita.com independent and running.
