The company described each area in its own words, without measured results. Google said Lyria 3.5 lets users \u201ccreate richer, more complex melodic structures that sound more natural,\u201d and generate \u201chigher quality lyrics with improved prompt adherence and structural awareness.\u201c<\/p>\n
Expecting A Minor update? We prefer to B Major. \ud83c\udfb6@GoogleDeepMind<\/a> just released Lyria 3.5, and we\u2019ve plugged it directly into @GoogleFlowMusic<\/a> to power your next session.<\/p>\n What this means for your tracks:<\/p>\n \u2728 Better prompt adherence: Flow Music understands your creative\u2026 pic.twitter.com\/mXikwIqC6I<\/a><\/p>\n \u2014 Google Labs (@GoogleLabs) July 29, 2026<\/a> <\/p>\n Vocals and Lyrics Carry the Upgrade<\/p>\n Vocals drew the most specific language in the release. Google said the model brings \u201cmore realistic and emotionally nuanced vocals, plus improved pronunciation,\u201d and that users can \u201cmore easily control the tempo and duration of your outputs.\u201c<\/p>\n The previous model sets the baseline for what changed. Google shipped Lyria 3 Pro on March 25, 2026<\/a>, lifting the track ceiling to three minutes from 30 seconds and letting users define intro, verse, chorus, and bridge sections. Every Lyria 3 Pro output carried a SynthID watermark.<\/p>\n Google has not said how the new duration control interacts with that three-minute ceiling.<\/p>\n A Realism Gain Lands in a Fraud-Heavy Market<\/p>\n Vocal realism is the axis where synthetic music becomes hard to police. Human detection accuracy for deepfakes can fall to 24.5% on high-quality media, according to AI voice cloning fraud data<\/a>, which also puts the global AI voice cloning market at $4.06 billion in 2026 on a Research and Markets projection.<\/p>\n Streaming platforms are already absorbing the volume. Sony Music removed 135,000 AI generated songs falsely attributed to its artists, and Spotify opened a beta artist approval tool<\/a> that lets artists review releases before they appear under their names. AI reaches music platforms from other directions too, including Spotify\u2019s Claude-powered recommendations<\/a>.<\/p>\n Artists with catalogs on major services can check today whether their distributor or platform offers a release approval control and switch it on. It helps reduce the risk of a synthetic track landing on their profile, and it does nothing about uploads posted under a different name.<\/p>\n \t\t\t\t\t Don\u2019t chase tech news. We track it for you.<\/p>\n One weekly briefing with the launches, AI developments, and breaches that matter. No filler.<\/p>\n What the Launch Post Left Out?<\/p>\n Google\u2019s announcement runs to four bullet points and a rollout line. Five things it does not answer:<\/p>\n Whether SynthID watermarking applies to Lyria 3.5 output, as Google confirmed for Lyria 3 Pro.<\/p>\n What Google Flow Music costs, or whether Lyria 3.5 sits behind a paid tier.<\/p>\n Which countries receive the model, and on what schedule.<\/p>\n What the new duration control tops out at.<\/p>\n Whether any listening test compared Lyria 3.5 against the previous model.<\/p>\n Google published no evaluation data alongside the release. \u201cMore realistic\u201d and \u201chigher quality\u201d are the company\u2019s characterizations of its own model, and no outside party has measured either one.<\/p>\n SQ Magazine\u2019s Takeaway<\/p>\n Lyria 3.5 moves the two variables that decide whether a generated song passes as human. Google\u2019s own list points at both, promising better pronunciation and more emotional nuance than the model delivered before, alongside direct control over tempo and length. That aims the release at creators who want a finished song out of the tool.<\/p>\n What comes next sits with the platforms more than the model. Detection and attribution tooling on streaming services was built against an earlier generation of output, and a vocal upgrade tests it directly. Two things are worth watching: whether Google states that SynthID covers Lyria 3.5, and whether streaming services say how their screening handles the new output.<\/p>\n![\"Newsletter\"](\"https:\/\/www.europesays.com\/ai\/wp-content\/uploads\/2026\/04\/newsletter.png\")
<\/p>\n