Google DeepMind and the Gemini team announced on February 18, 2026 that Lyria 3 is rolling out in beta in the Gemini app. Users can generate 30-second tracks from text, photos, or videos, and all outputs include SynthID watermarking.
Google DeepMind has released Lyria 3, its most advanced generative music model, now available in the Gemini app. The model creates 30-second tracks with vocals and auto-generated lyrics from text prompts or image uploads, with SynthID watermarking for AI detection.
Google announced on 2026-02-18 that Lyria 3 is rolling out in beta in the Gemini app. The feature generates 30-second tracks from text or images, attaches generated cover art, and embeds SynthID watermarking for AI-content identification.
Google announced on February 18, 2026 that Lyria 3 music generation is rolling out in beta in the Gemini app. Users can create 30-second tracks from text or images, and all generated audio is marked with SynthID.