According to Google Gemini on X, Lyria 3—its most advanced music model—now enables users to generate 30-second custom soundtracks in beta directly in Gemini using text, images, or video as prompts (source: Google Gemini). As reported by the GeminiApp post, this multimodal workflow streamlines music creation for short-form video, ads, trailers, and social content, reducing production time and licensing friction for creators and marketers (source: Google Gemini). According to the announcement, the feature targets rapid soundtrack prototyping and vibe matching, hinting at new monetization paths for creative tools and potential integrations with content platforms seeking scalable, rights-safe audio generation (source: Google Gemini).

According to Google DeepMind on X, musician Wyclef used the Lyria model to help develop his latest track “Back from Abu Dhabi,” demonstrating AI-assisted composition, sound design, and arrangement in a professional workflow. As reported by Google DeepMind, Lyria provides controllable music generation that can align to artist prompts and structure, enabling faster ideation and iterative refinement for studio output. According to Google DeepMind, the collaboration highlights business opportunities for labels and creators including scalable demo creation, rights-managed stems, and rapid A/B testing of melodies and instrumentations using Lyria’s controllable outputs.

According to Google Gemini on X (@GeminiApp), Gemini’s music prompting flow now offers dynamic suggestions that propose descriptive styles, instruments, and moods as users type, enabling easier remixing and refinement of audio prompts. As reported by the official Gemini post, this UI enhancement lowers prompt engineering friction for generative audio workflows, potentially improving output quality and speed for creators and marketers building short-form music beds, jingles, and ad soundscapes. According to Google Gemini, the feature encourages iterative prompt authoring, which can reduce trial-and-error cycles and help non-experts reach production-ready prompts faster—an efficiency gain relevant for studios, agencies, and UGC platforms that need rapid, on-brand audio variations.

According to @elevenlabsio, the newly launched Eleven Music API is the first AI music API for developers trained exclusively on licensed data and cleared for comprehensive commercial use. This enables businesses to seamlessly integrate high-quality AI-generated music into their products and workflows, addressing a significant need for copyright-safe audio content in various industries. Since its launch, creators have already generated over 750,000 songs using Eleven Music, demonstrating strong demand and opening new business opportunities for platforms seeking scalable, AI-driven music solutions (source: ElevenLabs Twitter, June 2024).