Google DeepMind's Lyria 3.5 lands in Flow Music, promising better vocals and lyrics
The new model aims for richer melodies, cleaner pronunciation, and more control over tempo and track length.
Key points
- Google DeepMind released Lyria 3.5, its newest AI music generation model, inside Flow Music on the launch day.
- The update targets four areas: musicality, lyrics, vocals, and creative controls like tempo and duration.
- Vocals are meant to sound more expressive and pronounce words more accurately than the previous version.
- Flow Music is Google's consumer tool for making full songs from written prompts.
- No pricing changes or new safety details were announced alongside the model.
Google DeepMind has rolled out Lyria 3.5, the latest version of its AI music generation model, the software that turns a written prompt into a full song. It is live now inside Flow Music, Google's tool for making tracks from a description.
The pitch is straightforward. Better melodies, better lyrics, better singing voices, and more say over how long the track runs and how fast it moves.
What actually changed?
Four things, according to Google. Melodies are meant to feel more natural and less repetitive. Lyrics should follow your prompt more closely and have a clearer verse-and-chorus shape.
The synthetic vocals, the AI-generated singing, are the headline. Google says they carry more emotion and pronounce words more accurately, which has been a weak spot for text-to-music tools until now.
On the controls side, you can more easily set the tempo (how fast the song plays) and the total length of the output. Small changes, but ones that matter if you are actually trying to finish a song rather than just play with a demo.
| Area | What Lyria 3.5 promises |
|---|---|
| Musicality | Richer, more complex melodies |
| Lyrics | Better prompt adherence and song structure |
| Vocals | More expression, cleaner pronunciation |
| Controls | Tempo and duration adjustments |
Where can people try it?
Inside Flow Music, Google's consumer music creation product. Google says the update is available today, no waitlist mentioned.
Flow Music sits alongside the company's other creative tools built on DeepMind research. It is aimed at hobbyists and creators who want a finished track rather than a raw audio clip.
What this means for listeners and creators
For listeners, it means more AI-generated songs are about to appear on social feeds, and they will be harder to tell apart from human recordings. Cleaner vocals and better lyric structure are exactly the things that used to give AI music away.
For working musicians and producers, the practical questions are the ones Google did not answer in this announcement: how the model was trained, what data it learned from, and what rights users get over the songs they generate. Music generation tools have faced ongoing legal scrutiny over training data from record labels and rights holders, and Lyria 3.5's launch post does not address that.
For everyone else, this is another step in a fast-moving stretch of AI music releases. The gap between "obviously a robot" and "could be a real singer" is closing quickly.
What to watch for
A few things worth keeping an eye on as Lyria 3.5 spreads.
Listen for the pronunciation. Older AI vocal models slurred consonants or mangled unusual words, and that has been the easiest tell. If Google's claim holds up, that tell is going away.
Watch how platforms label AI-made music. If a track sounds fully produced and the vocals sound human, the label in the corner of the app may be the only signal you get. Google has not detailed how Flow Music outputs will be watermarked or tagged when shared elsewhere.
And if you are a creator uploading AI-assisted songs to streaming services, check each platform's disclosure rules. Spotify, YouTube and others have updated their policies on AI-generated content over the past year, and enforcement is tightening.
Credit to the DeepMind team behind the Lyria line for shipping the update with specific claims attached rather than vague promises. The proof will be in what people make with it this week.
