Google has introduced a new capability for Google Gemini, allowing users to generate short music tracks directly within the app. The feature, currently rolling out in beta, enables AI-driven creation of 30-second songs based on text prompts, photos, or videos.
The music generation tool is powered by Google DeepMind’s latest generative model, Lyria 3, marking another step in Google’s expansion of creative AI tools across its ecosystem.
AI Music Creation Arrives in Gemini
With this update, Gemini users can produce short audio tracks by simply describing a concept, genre, mood, or memory. The AI automatically generates:
- Lyrics (if requested)
- Instrumental compositions
- Cover artwork for the track
The feature is launching in beta across multiple languages, including English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. Access is limited to users aged 18 and above, with higher usage limits available to paid subscribers under Google AI Plus, Pro, and Ultra tiers.
Google says the goal is not to replace professional music production but to offer a creative tool for personal expression and social sharing.
How the Feature Works
Users can prompt Gemini with creative directions such as:
- Specific genres or moods
- Personal memories or inside jokes
- Visual inspiration via photos or videos
Gemini then generates a 30-second track aligned with the request. If lyrics are included, the AI writes them automatically, eliminating the need for user input.
Artwork for the generated song is created using Google’s Nano Banana image system, further enhancing the shareable nature of the content.
Safeguards and Responsible AI Measures
To address copyright and authenticity concerns, Google has embedded generated tracks with SynthID, its invisible watermarking technology designed to identify AI-created content.
The company also states that music generation is intended for original expression rather than imitation of specific artists. If users mention a musician in prompts, Gemini interprets it as broad stylistic inspiration rather than direct mimicry.
Additionally, built-in filters aim to detect similarities with existing copyrighted works, and users can report content that may infringe on rights.
What This Means for AI Creativity
The rollout highlights growing competition among tech companies to integrate generative media tools into consumer AI platforms. By adding music creation, Gemini expands beyond text and image generation into multimodal creative output.
For users, this could open new opportunities for:
- Social media content creation
- Quick soundtrack generation for videos
- Experimentation with songwriting ideas
- Personalized digital expression
However, limitations such as short track length and beta status suggest the feature is still in its early development phase.
Frequently Asked Questions
How long are Gemini-generated music tracks?
Currently, Gemini can create tracks up to 30 seconds in length during the beta phase.
Can Gemini imitate specific artists?
No. Gemini uses artist names only as broad stylistic inspiration and includes safeguards to prevent direct imitation.
Is Gemini music generation available to everyone?
The feature is available to users aged 18 and above, with higher usage limits offered to Google AI Plus, Pro, and Ultra subscribers.
