Google DeepMind Launches Lyria 3.5 In Flow Music
Google DeepMind announced on July 29, 2026 that it is rolling out Lyria 3.5, which it calls its newest music generation model, in Google Flow Music. The company describes advances in four areas. Improved musicality: the model can create richer, more complex melodic structures that sound more natural. Enhanced lyrics: higher quality lyrics with improved prompt adherence and structural awareness. Improved vocals: more expression and emotion, more realistic and emotionally nuanced vocals, plus improved pronunciation. Creative control: easier control over the tempo and duration of your outputs. Google says it is rolling out today and invites people to try it in Flow Music.
Transcript
Google DeepMind said today it is rolling out Lyria three point five, its newest music generation model.
Lyria three point five is rolling out today in Google Flow Music. Google says it can create richer, more complex melodic structures that sound more natural.
Google also lists better lyrics with improved prompt adherence, more expressive vocals with better pronunciation, and easier control over the tempo and duration of outputs.
Google described these improvements in general terms. It published no benchmarks and no numbers, so the real test is what people actually produce with the model.
Inboxsmith helps small businesses handle calls and messages so nothing gets missed. Please like and subscribe for more news.
Sources
Every claim in this video comes from the top ranking coverage of this topic. The claims and where each one came from:
- Lyria 3.5 is Google DeepMind's newest music generation model(Google DeepMind official announcement)
- Lyria 3.5 is rolling out today in Google Flow Music(Google DeepMind official announcement)
- Improved musicality means richer, more complex melodic structures that sound more natural(Google DeepMind official announcement)
- Enhanced lyrics have higher quality with improved prompt adherence and structural awareness(Google DeepMind official announcement)
- Improved vocals are more realistic and emotionally nuanced, with improved pronunciation(Google DeepMind official announcement)
- Creative control lets users more easily control the tempo and duration of outputs(Google DeepMind official announcement)
- The announcement describes the improvements in general terms and includes no benchmarks or numbers(Google DeepMind official announcement)