Google DeepMind Blog

我们在Google Flow Music中推出Lyria 3.5，在音乐性、歌词、人声和创意控制方面取得进展。

Google DeepMind发布了最新的音乐生成模型Lyria 3.5，现已在Google Flow Music中上线。此次更新在音乐性上实现了更丰富的旋律结构；歌词方面提升了提示遵循度和结构意识；人声更加富有表现力和情感，发音更清晰；并增加了对节奏和时长的创意控制。用户即日起可在Flow Music中体验，创作更精致的音乐作品。

状态已摘要
抓取快照1
AI 输出2
开放问题0

已验证摘要

英文摘要

We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control.

Google DeepMind has launched Lyria 3.5, the newest music generation model, now available in Google Flow Music. This update brings significant improvements in musicality, enabling richer melodic structures; enhanced lyrics with better prompt adherence and structural awareness; more expressive and emotionally nuanced vocals with improved pronunciation; and greater creative control over tempo and duration. Users can try it today in Flow Music to create more refined tracks.

  • Lyria 3.5 launches today in Google Flow Music
  • Improved musicality with more complex melodic structures
  • Enhanced lyrics with better prompt adherence and structural awareness
  • Improved vocals with more expression, emotion, and pronunciation
  • Creative control over tempo and duration of outputs

中文摘要

我们在Google Flow Music中推出Lyria 3.5，在音乐性、歌词、人声和创意控制方面取得进展。

Google DeepMind发布了最新的音乐生成模型Lyria 3.5，现已在Google Flow Music中上线。此次更新在音乐性上实现了更丰富的旋律结构；歌词方面提升了提示遵循度和结构意识；人声更加富有表现力和情感，发音更清晰；并增加了对节奏和时长的创意控制。用户即日起可在Flow Music中体验，创作更精致的音乐作品。

  • Lyria 3.5今日在Google Flow Music中发布
  • 改善的音乐性，支持更复杂的旋律结构
  • 增强的歌词功能，更好的提示遵循度和结构意识
  • 改进的人声，更富有表现力和情感，发音更准确
  • 对输出节奏和时长的创意控制

Google DeepMind / Lyria / music generation / AI / Google Flow Music / musicality / lyrics / vocals / creative control / model / Google Labs

完整文章

We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control.Jul 29, 2026Our 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 .POSTED IN:Related stories

Google LabsGoogle and KDDI are ready to back Japanese startups.

By

Jonathan Silber

Google DeepMindReconstructing Pelé’s “lost” goal

By

Anita Lucchesi

&

Gabe Ferreira

Google CloudWe're rolling out AlphaEvolve widely to solve Google Cloud customers' hardest problems.

By

Tom Beyer

AIThe latest AI news we announced in June 2026

By

News from Google Team

阅读原文 →

抓取快照

用于解析和审计的抓取证据。

200 · text/html; charset=utf-8

2026/07/30 08:00

218947ddb23327c2be814652563d8ed434124becc10b6918507bc0338c0736f8

AI 输出

带验证状态的结构化模型输出。

article.summarize

deepseek-v4-flash · 有效

{"tags":["Google DeepMind","Lyria","music generation","AI","Google Flow Music","musicality","lyrics","vocals","creative control","model","Google Labs"],"titleEn":"We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control...
article.classify

deepseek-v4-flash · 有效

{"relevant":true,"confidence":0.95,"primaryTopic":"product-updates","secondaryTopics":["ai-research"]}

质量问题与日报引用

开放或已解决的问题，以及文章出现在每日日报中的记录。

日报

Signal Hub 2026-07-30

Google DeepMind重大AI音乐模型更新，在音乐性、歌词和人声方面有显著提升，现已在Flow Music中供创意专业人士使用。 (score: 0.95)

排序 12026/07/30 00:00草稿