Google has officially launched Lyria 3 integration for Gemini, allowing users to generate high-quality music tracks directly within the chatbot. This new feature enables the creation of audio clips up to 30 seconds long using simple prompts.
Key Features of Lyria 3 in Gemini
- Multimodal Inputs: Generate music from text descriptions, images, or videos.
- Automatic Composition: The AI produces instruments, lyrics, and vocals based on the specified genre, mood, or situation.
- Visual Assets: Gemini automatically generates cover art for every track to simplify sharing.
- Multilingual Support: Available in eight languages, including English, Portuguese, Spanish, German, French, Hindi, Japanese, and Korean.
Availability and Usage
The feature is currently in beta. It is rolling out first for desktop users, with mobile app support arriving soon. While available to general users over 18, subscribers to Google AI Plus, Pro, and Ultra plans enjoy higher usage limits.
Safety and Copyright
To address intellectual property concerns, Google has implemented several safeguards:
- Originality: The system is designed for "original expression" rather than imitating specific artists.
- SynthID: All generated tracks include an invisible watermark for identification.
- Verification Tool: Users can upload audio files to Gemini to verify if they were created by AI.
- YouTube Integration: Lyria 3 is also powering Dream Track for YouTube Shorts creators.
