Google rolls out Gemini Audio to improve real-time dialogue and speech recognition
Google's new Gemini Audio family aims to make your conversations feel more natural.
Google has unveiled Gemini Audio, a suite of three new AI models aimed at enhancing real-time dialogue and speech recognition. The newly introduced models are Gemini 3.5 Transcribe, Gemini 3.5 Live, and Gemini 3.5 Live Experimental. These models collectively form the overarching Gemini Audio system.
According to Google, these AI models are designed to facilitate more natural and responsive conversations, improving dialogue and speech recognition capabilities. The trio of AI models will be rolled out for all Google users in various applications, including Search Live, Gemini Live, Docs, Keep, Gmail, the Gemini app, and Gboard.
This development comes shortly after Google launched its initial Gemini 3.5 models. Since then, the company has released Gemini 3.6 and Gemini 3.7. Despite the rapid advancements in AI technology, Google continues to refine the Gemini 3.5 family, introducing the new members in the form of Gemini 3.5 Transcribe, Gemini 3.5 Live, and Gemini 3.5 Live Experimental.
Written by urgent.news from Android Authority's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- Google brings Gemini Enterprise to lawyers with new AI tools, automation plug-ins indianexpress.com
- Google just fixed one of the most annoying things about talking to AI — Gemini Live can finally handle interruptions techradar.com
- Google launches Gemini 3.5 Transcribe, which powers Gboard Rambler & is coming to Chrome 9to5google.com
- Gemini's one billion users can't hide Google's cash flow crisis androidpolice.com
