Build with Lyria 3, our newest music generation model

2026-03-25 · Source: AI · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Music Generation · Depth: Intermediate, medium

Summary

Google has released Lyria 3 and Lyria 3 Pro, its newest music generation models, in public preview for developers via the Gemini API and Google AI Studio as of March 25, 2026. Lyria 3 combines deep musical awareness with structural coherence, enabling high-fidelity compositions with consistent vocals, verses, and choruses. Developers can choose between Lyria 3 Pro, designed for full-length songs up to three minutes with professional structural awareness, and Lyria 3 Clip, optimized for speed and high-volume requests, generating 30-second clips. Both models support realistic, expressive vocals in multiple languages and genres. Lyria 3 also introduces granular controls like tempo conditioning, time-aligned lyrics, and multimodal image-to-music input to influence mood and style.

Key takeaway

For AI Engineers building audio applications, Lyria 3 offers a robust solution for generating high-quality, structured music. You should explore Lyria 3 Pro for full-length tracks or Lyria 3 Clip for rapid prototyping and short-form content, leveraging its multimodal input and granular controls to achieve precise creative outcomes. Integrate the models via the Gemini API or experiment directly in Google AI Studio to quickly develop new audio experiences.

Key insights

Lyria 3 offers AI music generation with structural coherence, expressive vocals, and granular control via text and multimodal inputs.

Principles

• AI music generation benefits from structural coherence.
• Multimodal input enhances creative control in AI.
• Digital watermarking ensures transparency in AI-generated content.

Method

Lyria 3 allows music generation via natural language prompts, supporting tempo conditioning, time-aligned lyrics, and image-to-music input, with dedicated text and composer modes in AI Studio.

In practice

• Generate background music for videos.
• Create personalized alarm clock melodies.
• Develop social media audio assets.

Topics

• Music Generation AI
• Lyria 3
• Multimodal AI
• Gemini API
• SynthID Watermarking

Best for: AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• Google adds AI music generation to Gemini with Lyria 3 — Google's Lyria 3 model enables AI music generation in Gemini and YouTube, featuring mood-matching and content identification.
• Google DeepMind Releases Lyria 3: An Advanced Music Generation AI Model that Turns Photos and Text into Custom Tracks with Included Lyrics and Vocals — Lyria 3 is a multimodal AI generating high-fidelity music with vocals and lyrics from text and photos.
• Lyria 3 Pro: Create longer tracks in more — Lyria 3 Pro extends AI music generation to 3-minute tracks with structural control across Google's ecosystem.
• Google launches AI music generator Lyria 3 Pro, says it was trained on data it has the right to use — Google's Lyria 3 Pro advances AI music generation with improved structural understanding and broad platform integration.
• Record scratch—Google's Lyria 3 AI music model is coming to Gemini today — Google's Gemini app now offers AI music generation with Lyria 3, featuring SynthID watermarking and copyright considerations.
• A new way to express yourself: Gemini can now create music — Gemini now offers AI-powered music generation via Lyria 3, complete with watermarking for content identification.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by AI.