Real-time music generation just moved from demo to product. deepmind's lyria2, announced september…
real-time music generation just moved from demo to product. deepmind's lyria2, announced september 15, generates music in real time as you interact, after lyria 3.5 brought superior vocals to the gemini app and api.
the copyright question will outlive the wow.
Context
Two separate Google items are grounded. Google's post of September 4, 2026 says Lyria 3.5 is now available in the Gemini app and the Gemini API, with more expressive vocals and richer musical arrangements. Separately, the Gemini API docs describe Lyria RealTime as an experimental model with a persistent, bidirectional, low-latency streaming connection over WebSocket, and DeepMind's page says it creates a continuous stream of music that can be steered in real time.
No first-party September 15 announcement of a model called Lyria 2 was located, and the real-time model in the pages read is named Lyria RealTime. Its docs mark it experimental. That alone does not establish that it is unusable, but a dated move from demo to product is not supported by what was read. No latency figure, hardware or conditions were stated beyond low-latency. Superior vocals is the note's wording, and Google's is more expressive vocals.
Watch next
- A first-party DeepMind post dated September 15, 2026 if one exists, and RealTime leaving experimental status.
Sources
- Google: better tracks with Lyria 3.5 in Gemini (September 4, 2026)blog.google
- Gemini API docs: real-time music generationai.google.dev
- DeepMind: Lyria RealTimedeepmind.google
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 21:47 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →