We’re launching Lyria 3.5 in

AI 中文解读

Google DeepMind推出新一代音乐生成模型Lyria 3.5，并已整合进Flow Music应用。这版模型在旋律、歌词和人声表现上全面升级，生成的作品更自然动听，歌词也更贴合创作意图，还支持更灵活控制歌曲速度和长度。简而言之，以前AI生成的歌曲容易有“塑料感”，歌词也经常不知所云；现在Lyria 3.5让AI谱曲更流畅、歌词更有逻辑，演唱也带上真情实感，几乎能以假乱真。对普通人来说，这意味着不用学乐理、不用练唱功，只要输入几句想法或歌词，就能在手机上捣鼓出水准不错的完整歌曲，无论是做短视频配乐、自娱自乐还是给朋友准备惊喜小礼物，都变得触手可及。音乐创作的门槛，正在被AI进一步拉低。

{ "reading_time": "[[read\u002Dtime]] min read" } Breadcrumb Home Innovation & AI Models & research Google Labs We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control. Jul 29, 2026 Our newest music generation model, Lyria 3.5, delivers significant advancements across musicality, lyrics, and vocal quality, empowering you to craft richer tracks. We’re rolling it out today in Google Flow Music, where we want to help you create songs you love, with creative control.Here's what’s new:Improved musicality: Create richer, more complex melodic structures that sound more natural.Enhanced lyrics: Generate higher quality lyrics with improved prompt adherence and structural awareness.Improved vocals: Bring more expression and emotion to your songs with more realistic and emotionally nuanced vocals, plus improved pronunciation.Creative control: More easily control the tempo and duration of your outputs.Try it today in Flow Music. { "@context": "https://schema.org/", "@type": "VideoObject", "name": "Introducing Lyria 3.5 now available in Google Flow Music", "description": "Hear a track created with Lyria 3.5", "thumbnailUrl": "https://i.ytimg.com/vi_webp/WQkg3n5bwKQ/maxresdefault.webp", "uploadDate": "2026-07-29T16:00:00+00:00", "contentUrl": "https://www.youtube.com/watch?v=WQkg3n5bwKQ", "embedUrl": "https://www.youtube.com/embed/WQkg3n5bwKQ" }