{"id":575388,"date":"2026-07-30T12:00:09","date_gmt":"2026-07-30T12:00:09","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/575388\/"},"modified":"2026-07-30T12:00:09","modified_gmt":"2026-07-30T12:00:09","slug":"watch-out-suno-google-has-upgraded-its-lyria-ai-music-model-with-more-realistic-and-emotionally-nuanced-vocals","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/575388\/","title":{"rendered":"Watch out, Suno: Google has upgraded its Lyria AI music model with \u2018more realistic and emotionally nuanced vocals\u2019"},"content":{"rendered":"

Google<\/a> has launched Lyria 3.5, the latest version of its AI music-generation model, promising tracks that \u201csound more natural\u201d and vocals with \u201cmore expression and emotion.\u201d<\/p>\n

The model rolled out on Wednesday (July 29) inside Google Flow Music, the company\u2019s AI song-creation platform.<\/p>\n

Google DeepMind, the tech giant\u2019s AI research division, said Lyria 3.5 delivers \u201csignificant advancements across musicality, lyrics and vocal quality.\u201d<\/p>\n

On vocals, Google said the model can \u201cbring more expression and emotion to your songs with more realistic and emotionally nuanced vocals, plus improved pronunciation.\u201d<\/p>\n

On musicality, Google said users can create \u201cricher, more complex melodic structures that sound more natural.\u201d<\/p>\n

The company also cited \u201chigher quality lyrics\u201d with better prompt adherence, and easier control over the tempo and duration of a track in Flow Music.<\/p>\n

To showcase the capabilities of Lyria 3.5, Google released the following track, which features the vocal style of a female pop artist.<\/p>\n

What Google\u2018s announcement did not say is how Lyria 3.5 was trained.<\/p>\n

The blog post also made no mention of SynthID, the watermarking technology Google embeds in its AI-generated tracks, nor of the copyright framing that accompanied earlier Lyria launches.<\/p>\n

When Google launched Lyria 3 in February, it described that model as \u201cdesigned for original expression, not for mimicking existing artists.\u201d<\/p>\n

Google said at the time that it had been \u201cvery mindful of copyright and partner agreements,\u201d and that it had sought to \u201cdevelop this technology responsibly in collaboration with the music community.\u201d<\/p>\n

The Lyria 3.5 announcement carried no equivalent language.<\/p>\n

Unlike the Lyria 3 launch, which was bylined by two Google product managers, it also carried no named author.<\/p>\n

Google has never specified what music it used to train the Lyria model line.<\/p>\n

The company has said its training uses material that it and YouTube<\/a> \u201chave the right to use\u201d under their \u201cterms of service, partner agreements, and applicable law.\u201d<\/p>\n

Google\u2018s position is now being tested in court.<\/p>\n

In March, a group of independent musicians and songwriters sued Google<\/a>, accusing it of training Lyria 3 on copyrighted recordings pulled from YouTube without permission or payment.<\/p>\n

Their 118-page complaint claimed Google had copied \u201cat least 44 million clips and 280,000 hours of music.\u201d<\/p>\n

The plaintiffs argued that Google holds \u201cstructural leverage\u201d because it owns YouTube and runs Content ID, the platform\u2019s rights-management system.<\/p>\n

Google moved to dismiss<\/a> the case in June.<\/p>\n

Its lead argument is not a fair use defense, but that the musicians licensed their recordings to YouTube \u2013 and to Google \u2013 when they uploaded them.<\/p>\n

Each plaintiff, Google said, granted YouTube and its \u201cAffiliates\u201d a \u201cworldwide, non-exclusive, royalty-free, sublicensable and transferable license\u201d to use their uploaded content.<\/p>\n

The lawsuit, Google added, rests on the \u201cunsupported hypothesis that Google trained on their specific works.\u201d<\/p>\n

Google DeepMind first unveiled Lyria in November 2023, in partnership with YouTube.<\/p>\n

It arrived alongside Dream Track, a YouTube Shorts experiment that generated tracks using AI voice clones of artists including Charlie Puth, T-Pain and Alec Benjamin.<\/p>\n

A later model, Lyria 2, powered YouTube\u2018s \u201cSpeech to Song\u201d tool for turning dialogue into music.<\/p>\n

Lyria 3 followed<\/a> in February 2026 inside Google\u2019s Gemini app, generating 30-second tracks from text prompts or images.<\/p>\n

Flow Music, where Lyria 3.5 now sits, began as Riffusion, an open-source project that went viral in 2022, and launched as ProducerAI in 2025.<\/p>\n

Google acquired the platform in February and rebranded it Flow Music in April.<\/p>\n

In May, Believe<\/a> partnered with Google to offer Flow Music to artists across the distributor and its self-release arm, TuneCore<\/a>.<\/p>\n

\u201cThe adoption of Gen-AI is going to enhance human creativity,\u201d Believe founder and CEO Denis Ladegaillerie<\/a> told MBW at the time.<\/p>\n

Last week, Google added song generation, editing and stem splitting<\/a> to Spaces, a \u201cvibe coding\u201d tool inside Flow Music.<\/p>\n

The additions move Flow Music closer to rivals Suno and Udio.<\/p>\n

Universal Music Group<\/a> and Warner Music Group<\/a> both settled their copyright lawsuits against Udio, agreeing to build licensed AI music platforms. Sony<\/a> Music, however, has not settled with Udio and continues to litigate, filing a fresh suit on July 20 that names more than 30,000 recordings. Warner has also settled with Suno, while Universal and Sony\u2018s cases against Suno remain ongoing.Music Business Worldwide<\/p>\n","protected":false},"excerpt":{"rendered":"Google has launched Lyria 3.5, the latest version of its AI music-generation model, promising tracks that \u201csound more…\n","protected":false},"author":2,"featured_media":575389,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[61,60,80],"class_list":["post-575388","post","type-post","status-publish","format-standard","has-post-thumbnail","category-technology","tag-ie","tag-ireland","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/575388","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=575388"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/575388\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/575389"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=575388"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=575388"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=575388"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}