Lyria 3 Clip

Lyria 3 is Google DeepMind’s most advanced AI music generation model, designed to create high-fidelity, professional-grade audio from simple prompts. It enables users to describe a track in natural language and refine details such as tempo, vocal style, and instrumentation for greater creative control. The model can generate cohesive songs that flow naturally from start to finish across a wide range of genres and global languages. Lyria 3 also supports image-to-music composition, allowing users to upload visuals and transform them into custom soundtracks. Built with input from musicians and producers, it understands rhythm, arrangement, and musical structure at a deeper level. Users can export crisp, polished tracks suitable for background ambience, content creation, or mainstage productions. Integrated into Gemini and other creative tools, Lyria 3 empowers creators to explore, experiment, and express ideas through AI-driven music.

Lyria 3.5 is Google’s newest AI music generation model, designed to help people create richer, high-fidelity tracks with greater musical and technical control. Available in Google Flow Music, it advances musicality with more natural, complex melodic structures and a stronger understanding of rhythm, arrangement, tempo, dynamics, and more. Enhanced lyric generation improves prompt adherence and structural awareness, while upgraded vocals add more realistic expression, emotional nuance, and clearer pronunciation. Users can begin with a simple idea or provide detailed instructions for genre, instrumentation, mood, key, tempo, vocal style, language, and production character, then refine the sound they want. Lyria 3.5 supports variable song lengths, allowing creators to request a quick 60-second clip, a half-length track, or a cohesive song lasting up to three minutes. It can generate music across global languages and genres, from pop, funk, and R&B to reggaeton, jazz, and electronic music.