Tech Meridian ← LIVE FEED
RU

NEWS · MODELS · #57

Build real-time voice applications with Gemini 3.8 Live and 3.5 Transcribe

Google is making Gemini 3.8 Live and Gemini 3.5 Transcribe available to try for building real-time voice applications; the models can be tested at ai.studio/live.

KEY POINTS

  1. Google is making Gemini 3.8 Live and Gemini 3.5 Transcribe available to try for building real-time voice applications; the models can be tested at ai.studio/live.
  2. Availability of these Gemini models matters because they provide Google-backed options for developers building live speech, transcription, or voice-interactive features.
  3. Build real-time voice applications with Gemini 3.8 Live and 3.5 Transcribe

WHY IT MATTERS

Availability of these Gemini models matters because they provide Google-backed options for developers building live speech, transcription, or voice-interactive features.

SOURCES & TIMELINE

1
01
GOOGLE FIRST-PARTY
Build real-time voice applications with Gemini 3.8 Live and 3.5 Transcribe

New Gemini Audio models are available for developers to build more intelligent conversational experiences via the Gemini API and Google AI Studio. Member of the Technical Staff (DevX), Google DeepMind Your browser does not support the audio element. Today, we released new Gemini Live models in the Gemini API and Google AI Studio , expanding our developer suite for building real-time, voice-first product experience…

↗