Google Launches Lyria3 AI Music Generation Model

Introduction to Lyria3

  • Google DeepMind has released Lyria3, which serves as their latest music generation system. The model creates high-quality music from simple text prompts. The feature supports both Android and iOS users.
  • The official blog post from Google DeepMind provides information about Lyria3. The company aims to support digital creators with easy music production tools.

Key Features of Lyria3

  • Lyria3 generates a 30-second music track based on user input. Users can define mood, tempo, and instrument. The system then produces music that matches those settings.
  • Users can also upload photos or videos. The model analyzes the content and creates suitable background music. The system generates music that matches the scene when a user uploads a sunrise or travel photo.

Watermark and Content Identification

Lyria3 music output contains an invisible watermark. The watermark serves to identify audio content which was produced using this model. The feature supports responsible content tracking.

Language and Access Availability

  • Lyria3 supports multiple languages. The languages supported by this system include English, Hindi, German, Spanish, French, and Korean.
  • Users aged 18 years and above can access the feature through Gemini with limited usage. Google AI Plus subscribers along with Pro and Ultra plan users can access the tool at higher usage levels.