Congrats to the @GoogleDeepMind team on an awesome model; 3.8 is a step change in gemini voice performance.
And shoutout to movie-star-in-the-making @valeriawu_
Explore the latest advances in native audio models and the challenges of building better real-time voice experiences with @GoogleDeepMind + @SierraPlatform.
Learn about conversational latency, multilingual code-switching, agentic voice tasks, and more →goo.gle/4hKV9B5
Voice agents are getting better at thinking and speaking at the same time, and in multiple languages. We’ve been working with @googlecloud and @GoogleDeepMind to test Gemini 3.8 Live Extended Thinking against real-world enterprise scenarios. The model scored 35.1% on Sierra’s τ-Voice-banking benchmark, while delivering low latency and competitive pricing.
Excited about what this unlocks for voice.
Explore the latest advances in native audio models and the challenges of building better real-time voice experiences with @GoogleDeepMind + @SierraPlatform.
Learn about conversational latency, multilingual code-switching, agentic voice tasks, and more →goo.gle/4hKV9B5