Vai al contenuto
AI.info

Model Tracker

Lyria RealTime

Lyria RealTime is an AI model made by Google DeepMind. Google DeepMind released it on 20 May 2025. It is in preview. It takes text and returns audio.

In inglese

Google DeepMind

Released
20 May 2025 — blog.google, read 16 October 2026
Status
Preview — ai.google.dev, read 16 October 2026
Takes
Text — ai.google.dev, read 16 October 2026
Returns
Audio — ai.google.dev, read 16 October 2026
Open weights
Not confirmed: The maker's pages do not state whether Lyria RealTime's weights are open or downloadable.
Licence
Not confirmed: The maker's pages do not publish a licence for Lyria RealTime itself.
Context window
Not confirmed: The maker's Lyria RealTime model page and API documentation do not state a context-window size in tokens.
Longest answer
Not confirmed: The maker's pages describe continuous audio streaming but do not state a standard maximum output limit in tokens.
Knowledge cutoff
Not confirmed: The maker's pages do not publish a knowledge-cutoff date for Lyria RealTime.
API price, input
Not confirmed: The maker's pricing page does not list a standard per-token input price for Lyria RealTime.
API price, output
Not confirmed: The maker's pricing page does not list a standard per-token output price for Lyria RealTime.
Where
API, Consumer app — blog.google, read 16 October 2026
Parameters
Not confirmed: The maker's pages do not publish a parameter count for Lyria RealTime.
Model card
Not confirmed: No model card or system card specifically for Lyria RealTime was found on the maker's pages.

Questions

When was Lyria RealTime released?

Google DeepMind released Lyria RealTime on 20 May 2025.

Is Lyria RealTime still available?

It is in preview: Google DeepMind has not made it generally available yet.

What does Lyria RealTime take and return?

Lyria RealTime takes text and returns audio.

More from Google DeepMind

Sources

  1. Lyria RealTime experimental (read 16 October 2026)
  2. Real-time music generation using Lyria RealTime (read 16 October 2026)
  3. Models (read 16 October 2026)
  4. New generative AI tools open the doors of music creation (read 16 October 2026)
  5. Fuel your creativity with new generative media models and tools (read 16 October 2026)
  6. Gemini Developer API pricing (read 16 October 2026)

All of the Model Tracker