Google DeepMind launches Lyria 3.5 music generation model in Flow Music
Google DeepMind has released Lyria 3.5, an updated music generation model, now available in Google Flow Music. The model offers improvements in musicality, lyrics, vocals, and creative control. Users can create tracks with more complex melodic structures, higher quality lyrics with better prompt adherence, and more expressive vocals with improved pronunciation. Creative control features allow adjustment of tempo and duration. The rollout began today.
Key facts
- Lyria 3.5 is a new music generation model from Google DeepMind.
- It is available in Google Flow Music.
- Improvements include musicality, lyrics, vocals, and creative control.
- Musicality: richer, more complex melodic structures.
- Lyrics: higher quality with improved prompt adherence and structural awareness.
- Vocals: more expressive, realistic, emotionally nuanced with improved pronunciation.
- Creative control: easier control of tempo and duration.
- The model launched today.
Entities
Institutions
- Google DeepMind
- Google Flow Music