Overview
On February 18, 2026, Google integrated Lyria 3 — its third-generation AI music generation model — directly into the Gemini platform. Users with Gemini access could now generate original music compositions through text prompts, with the output available as downloadable audio files.
Lyria 3 represented Google’s latest advancement in AI audio generation, with improved musical coherence, instrumentation fidelity, and prompt adherence compared to previous generations.
What Changed
Prior to this integration, AI music generation required separate applications (Suno, Udio) or specialized tools. With Lyria 3 in Gemini:
- Any Gemini user could generate music as part of a broader multimodal conversation
- Music generation was now accessible within the same interface used for text, image analysis, and coding assistance
- The integration signaled Google’s intent to make audio generation a first-class capability in consumer AI