Lyria 3.5 in Flow Music: Tempo Control Over Head-to-Head Benches
Google announced Lyria 3.5 in Flow Music, claiming improvements in musicality, lyrics and vocals plus easier tempo and duration control. Its announcement provides no comparative benchmark.
Correction / update, October 14, 2026: Removed unsupported watermarking, backend-replacement and competitor-comparison claims. Absence statements now refer only to the inspected announcement.
Music generation is a consumer multimodal lane labs treat as strategically important for engagement. Google’s stake here is productized control inside Flow—tempo, duration, iterate—not a research demo or an open-weight release.
Google launched Lyria 3.5 in Google Flow Music. The Google Labs primary highlights four product claims: richer musicality, higher-quality lyrics with better prompt adherence, more expressive vocals, and easier tempo and duration control. The announced surface is Flow Music. This particular post does not announce a standalone third-party API.
What shipped#
| Item | Detail (Google primary) |
|---|---|
| Model | Lyria 3.5 |
| Surface | Google Flow Music |
| Musicality | Richer, more complex melodic structures |
| Lyrics | Higher quality; improved prompt adherence and structural awareness |
| Vocals | More realistic / emotionally nuanced; improved pronunciation |
| Controls | Tempo and duration of outputs |
Google frames Flow Music as the consumer create surface: generate songs you can control and iterate, not only one-shot clips.
Competitive context#
Google did not publish head-to-head benchmarks against Suno or Udio in the inspected Labs post. Its stated focus is creative control inside Flow Music.
Limits#
- This article does not establish an independent preference-board comparison with Suno or Udio.
- The inspected Labs post does not announce a developer API path.
- Musicality/lyrics/vocals claims are lab product framing.