<\/p>\n
Google<\/a> has launched what it says is its \u2018most advanced\u2019 generative AI music model yet, Lyria 3, within its Gemini chatbot app \u2014 allowing users to create 30-second tracks from text prompts or images.<\/p>\n Lyria 3 was developed by Google DeepMind<\/strong>, the tech giant\u2019s AI research division, and is the latest iteration of its generative music technology.<\/p>\n The feature, which began rolling out on Wednesday morning (February 18), enables users aged 18 and over to describe a genre, mood, or scenario and receive an AI-generated track complete with vocals and lyrics. Users can also upload photos or videos and have Gemini compose an accompanying soundtrack.<\/p>\n Google is positioning the tool for casual use cases such as custom birthday cards or \u201ca ballad from your pet\u2019s POV.\u201d Lyria 3 is available in English, German, Spanish, French, Hindi, Japanese, Korean and Portuguese.<\/p>\n Google has not specified how Lyria 3 was trained, but said in a blog post on Wednesday<\/a> (February 18) it has sought to \u201cdevelop this technology responsibly in collaboration with the music community\u201d and has \u201cbeen very mindful of copyright and partner agreements\u201d in training the model.<\/p>\n MBW understands that to mean the training for Lyria 3 uses music that YouTube<\/a> and its parent company, Google, \u201chave the right to use\u201d under their \u201cterms of service, partner agreements, and applicable law\u201d.<\/p>\n Billboard reported in January 2024<\/a> that Google had previously trained its AI music models on copyrighted recordings before approaching rights holders for licensing deals.<\/p>\n Google said Lyria 3 represents an improvement on its previous Lyria models, offering automatically generated lyrics, greater creative control over style and tempo, and \u201cmore realistic and musically complex tracks.\u201d<\/p>\n The new model builds on Lyria 2, which MBW reported on in September<\/a>, and which powers YouTube\u2019s \u201cSpeech to Song\u201d tool for converting dialogue into musical soundtracks.<\/p>\n The company framed the feature as a tool for personal creative expression rather than professional music production. \u201cThe goal of these tracks isn\u2019t to create a musical masterpiece, but rather to give you a fun, unique way to express yourself,\u201d wrote Jo\u00ebl Yawili, Senior Product Manager at Gemini App, and Myriam Hamed Torres, Senior Product Manager at Google DeepMind, in a blog post<\/a> announcing the launch.<\/p>\n Lyria 3 is also being integrated into YouTube\u2019s Dream Track<\/a> \u2014 the platform\u2019s AI soundtrack generator for Shorts creators, first launched in 2023 \u2014 which is expanding beyond its initial US availability to creators in other countries.<\/p>\n Dream Track originally launched with AI voice clones of participating artists including Charlie Puth, T-Pain, and Alec Benjamin. Lyria 3 focuses on original vocal and instrumental generation rather than artist likeness.<\/p>\n The launch follows YouTube\u2019s rollout of a separate AI music tool, \u201cMusic Assistant,\u201d within its Creator Music marketplace earlier this year. That feature, which MBW reported on in April last year<\/a>, allows YouTube Partner Program members to generate copyright-free instrumental backing tracks via text prompts.<\/p>\n Google said that Lyria 3 is \u201cdesigned for original expression, not for mimicking existing artists.\u201d If a user\u2019s prompt names a specific artist, the company said, \u201cGemini will take this as broad creative inspiration and create a track that shares a similar style or mood.\u201d<\/p>\n The company added that it has \u201cfilters in place to check outputs against existing content\u201d and that users can report content that may violate their rights.<\/p>\n All tracks generated in Gemini are embedded with SynthID, Google\u2019s watermarking technology for identifying AI-generated content. The company also announced that users can now upload audio files to Gemini to check whether they were generated using Google AI.<\/p>\n The launch comes after Universal Music Group<\/a> and YouTube struck a new licensing deal in October<\/a> that included what UMG CEO Sir Lucian Grainge<\/a> called \u201creally important guardrails and protection for our artists and writers around gen AI content.\u201d<\/p>\n Music Business Worldwide<\/span><\/p>\n<\/div>\n \u2018 The preceding article may include information circulated by third parties \u2019 <\/em><\/p>\n \u2018 Some details of this article were extracted from the following source www.musicbusinessworldwide.com \u2019 <\/em><\/p>\n","protected":false},"excerpt":{"rendered":" Google has launched what it says is its \u2018most advanced\u2019 generative AI music model yet, Lyria 3, within its Gemini chatbot app \u2014 allowing users to create 30-second tracks from text prompts or images. Lyria 3 was developed by Google DeepMind, the tech giant\u2019s AI research division, and is the latest iteration of its generative […]<\/p>\n","protected":false},"author":2,"featured_media":2295043,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_jetpack_memberships_contains_paid_content":false,"jnews-multi-image_gallery":[],"jnews_single_post":[],"jnews_primary_category":[],"jnews_social_meta":[],"footnotes":""},"categories":[25179],"tags":[],"class_list":["post-2295042","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-music"],"jetpack_featured_media_url":"https:\/\/celebrity.land\/en\/wp-content\/uploads\/2026\/02\/Google-just-launched-Lyria-3-its-\u2018most-advanced-AI.jpg","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/posts\/2295042","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/comments?post=2295042"}],"version-history":[{"count":1,"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/posts\/2295042\/revisions"}],"predecessor-version":[{"id":2295044,"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/posts\/2295042\/revisions\/2295044"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/media\/2295043"}],"wp:attachment":[{"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/media?parent=2295042"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/categories?post=2295042"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/celebrity.land\/en\/wp-json\/wp\/v2\/tags?post=2295042"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n