Inside Lyria 3, Google's music generation model

About this episode

The episode features a discussion on Lyria 3, Google's music generation model, highlighting its capabilities and challenges.

Jeff Chang, Myriam Hamed Torres, and Jason Baldridge from the Google DeepMind team join host Logan Kilpatrick for a deep dive into Lyria 3, Google’s latest music generation model. Their conversation explores the transition from simple audio generation to a model that acts as a collaborative instrument, providing creators with fine-grained control over mood, instrumentation, and vocals. Learn more about the technical challenges of prompt adherence in music, the importance of "vibe" in human evaluations, and the future of layered, iterative music composition. Watch on YouTube: https://www.youtube.com/watch?v=mQUpaaU02DM

People in this episode

Host: Logan Kilpatrick

Guests: Jeff Chang, Myriam Hamed Torres, Jason Baldridge

Topics covered

• music generation
• AI technology
• collaborative instruments
• prompt adherence
• music composition

Keywords

• music generation
• AI
• Lyria 3
• Google DeepMind
• collaboration
• composition
• prompt adherence

Mentioned in this episode

Organizations: Google DeepMind, Google

Products: Lyria 3

More episodes of Google AI: Release Notes

• Google Maps Leaders Talk About Its Biggest Update in 10 Years · March 12, 2026 · 36 min
• Gemini in Workspace: New Ways to Create Faster · March 12, 2026 · 40 min
• Gemini in Chrome: Your agentic browsing assistant · March 12, 2026 · 49 min
• Project Genie: Create and explore worlds · January 30, 2026 · 43 min
• Gemini 3 and Gen UI in Google Search · December 18, 2025 · 22 min
• Sundar Pichai: Gemini 3, Vibe Coding and Google's Full Stack Strategy · November 26, 2025 · 28 min