Today, we’re advancing Gemini’s real-time dialogue capabilities with Gemini 3.1 Flash Live, our highest-quality audio and voice model yet. It delivers the speed and natural rhythm needed for the next generation of voice-first AI, offering a more intuitive experience for developers, enterprises and everyday users.
Advertising slot
What happened
Today, we’re advancing Gemini’s real-time dialogue capabilities with Gemini 3.1 Flash Live, our highest-quality audio and voice model yet. It delivers the speed and natural rhythm needed for the next generation of voice-first AI, offering a more intuitive experience for developers, enterprises and everyday users.
Why it matters
We’ve improved 3.1 Flash Live’s overall quality, making it more reliable for developers and enterprises to build voice-first agents that can complete complex tasks at scale. On ComplexFuncBench Audio , a benchmark that captures multi-step function calling with various constraints, it leads with a score of 90.8% compared to our previous model.
Advertising slot
What to watch next
On Scale AI’s Audio MultiChallenge , Gemini 3.1 Flash Live leads with a score of 36.1% with “thinking” on. The benchmark specifically tests complex instruction following and long-horizon reasoning amidst the interruptions and hesitations typical of real-world audio.
Source notes
- Google AI Blog official-site Global
From Patrick Tech
Contextual tools
AI Workspace Bundle for Digital Teams
A curated stack for writing, translation, summarization, and internal workflow speed.
Open Patrick Tech StoreCommunity
What did you think of this story?
Drop a reaction or leave a comment right below the article.
Latest comments
0No comments yet. You can start the conversation.