Post-Cutoff
Search For AI agents

Google DeepMindLyria familyPreviewMusic generation

Lyria RealTime

Real-time, steerable instrumental music stream for apps, installations and live performance. Use client.aio.live.music.connect(model="models/lyria-realtime-exp") in the Google Gen AI SDK.

Model idmodels/lyria-realtime-exp

PricePrice not published

Checked29 September 2026

Where it stands

No release date on file, so we can’t place it among other music generation models.

All music generation models

Weights
Closed weights; access is hosted only.

How to call it

Where to use Lyria RealTime, with its model id.

Providers, model ids, endpoints and docs for Lyria RealTime
ProviderModel idEndpointDocs
Gemini API (Live music, WebSocket) models/lyria-realtime-exp ai.google.dev

Pricing

Price not published.

No price source linked. Checked 29 September 2026.

Specs

Input
Text
Output
Audio
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
Not recorded
Status
Preview
Type
Music generation

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Interactive streaming music generation

    Persistent bidirectional WebSocket session that continuously streams 48 kHz stereo 16-bit PCM; steer live with weighted text prompts and play/pause/stop/reset controls.

    Source: ai.google.dev

  • Live musical parameters

    Adjust guidance (0-6), BPM (60-200), density, brightness, scale (12 key pairs) and mute bass/drums on the fly.

    Source: ai.google.dev

Notes

Experimental model (status ‘Experimental’ on the Gemini API models page; no shutdown date announced). Instrumental only; output is SynthID-watermarked. No price listed on the Gemini API pricing page as of 2026-09-29.

Sources: Lyria RealTime guide, models, deprecations.

Not yet checked against an official source: Release date not re-verified here (it first appeared in 2025 as an experimental model).