Lyria

What is Lyria?

Lyria is Google DeepMind’s AI music generation model family, designed to produce high-fidelity instrumental audio from text descriptions. First announced in April 2025 as Lyria 2, the model has since evolved through versions 3 and 3.5, each adding improved musical quality, longer-form composition capability, and finer creative control.

Unlike consumer-facing AI music generators, Lyria is primarily a developer and enterprise tool — available through Google’s Gemini API and Cloud platform rather than a simple web interface.

Key features

Fine-grained creative control over instruments, tempo (BPM), genre, and overall musical character — more precise than most text-to-music tools.

High-fidelity output that produces professional-grade instrumental audio suitable for production use.

Safety measures including content safety filters, recitation checking, and artist intent checks to prevent generation of harmful content.

SynthID watermarking on all generated audio for responsible AI identification.

Google ecosystem integration through the Gemini API, making it natural for developers already using Google Cloud services.

Limitations

Lyria is focused on instrumental music — it doesn’t generate vocals with lyrics. It’s primarily an API product rather than a consumer app, making it less accessible for casual users. And it’s not open source or free to run locally.

Who is Lyria for?

Lyria is best for developers integrating AI music into applications, enterprises building music features at scale, and musicians who want precise instrumental generation through an API. For full songs with vocals, ACE-Step UI or Suno are better choices. For a free, local alternative, ACE-Step UI is the clear winner.

Conclusion

Lyria represents Google’s serious investment in AI music generation. While it’s more of a developer tool than a consumer product, its quality, control, and ecosystem integration make it a powerful option for building music features into applications and services.

Official resource: Lyria