# clm_F572190FB860

subject: Google DeepMind (/record/google-deepmind.md)  
predicate: released  
value: Improved Gemini audio models  
valid_from: 2025-12-12  
valid_to: null  
published: 2025-12-12  
recorded: 2026-11-05  
confidence: 0.70  
status: valid  
assertable: true  
superseded_by: null  
last_updated: 2026-11-05  
checked: 2026-11-05 · its source page states the value and the date  

> Gemini 2.5 Native Audio upgrade, plus text-to-speech model updates. An upgraded Gemini 2.5 Native Audio model across Google products and live speech translation in the Google Translate app. Improved Gemini audio models for powerful voice interactions.

What https://deepmind.google/blog/improved-gemini-audio-models-for-powerful-voice-experiences/ says, word for word.

## Sources

- https://deepmind.google/blog/improved-gemini-audio-models-for-powerful-voice-experiences/ (primary, Google DeepMind, published 2025-12-12)

---

AsOf is a temporal fact ledger: a structured, dated, sourced record of what is true and what changed, built for AI retrieval.