Lyria 3

Overview

Lyria 3 is Google’s generative music and audio model, positioned as a developer-accessible media capability and surfaced both in the Gemini app and via API. Across the newsletter mentions, it is described as turning text prompts or images into original music, including short 30-second songs and, in Gemini app experiences, longer full-length tracks. Its rollout spans beta availability in Gemini, broader consumer access, and later API access for developers.

For AI Product Managers, Lyria 3 matters because it represents a practical multimodal generation tool that can power music creation, soundtrack generation, audio personalization, and creative workflow features inside products. It also signals how generative media products are evolving from showcase demos into deployable platform capabilities, with distribution through apps, monetization tiers, developer APIs, and provenance features like SynthID watermarking.

Key Developments

• 2026-02-19 — Google DeepMind rolled out Lyria 3 in beta globally via the Gemini app for custom audio generation. Outputs included SynthID, Google’s invisible watermark for AI-generated content.
• 2026-02-21 — Google AI highlighted Lyria 3 as a model that can turn photos or text into dynamic music, alongside other major product launches.
• 2026-04-10 — Josh Woodward announced full access to Lyria 3 in the Gemini app, including up to 5 free full-length (~3 minute) tracks per day, unlimited 30-second clips, and paid upgrades for additional generation.
• 2026-04-11 — DeepLearning.AI described Lyria 3 as an AI music generator that transforms text prompts or images into original 30-second songs.
• 2026-05-26 — Logan Kilpatrick announced that Lyria 3 became available via API, enabling developers to build directly with the model.

Relevance to AI PMs

• Designing multimodal creation features: Lyria 3 shows how text- and image-to-music can become a product feature for creator tools, marketing platforms, game experiences, social apps, or consumer media products.
• Planning packaging and monetization: The Gemini app rollout provides a concrete example of usage limits, free tiers, clip vs. full-track packaging, and upsell paths that PMs can adapt when launching generative media features.
• Managing trust, provenance, and compliance: The inclusion of SynthID highlights the need to think early about watermarking, disclosure, content authenticity, and policy controls when shipping AI-generated audio.

Related

• Google / Google AI / Google DeepMind — The organizations behind Lyria 3’s launch, beta rollout, and positioning within Google’s broader AI product ecosystem.
• Gemini app / GeminiApp — Early product surface where users accessed Lyria 3 for music generation before API availability.
• API — Marks Lyria 3’s transition from consumer-facing experience to developer platform capability.
• SynthID — Google’s invisible watermarking technology applied to Lyria 3 outputs for provenance of AI-generated media.
• Josh Woodward — Announced expanded Gemini app access and user-facing generation limits.
• Logan Kilpatrick — Announced API availability for developers.
• DeepLearning.AI — Covered Lyria 3 as a text/image-to-music generator, reinforcing its positioning for broader AI audiences.