Deep Learning
Google's latest AI audio model

Today, we're enhancing Gemini's real-time chat capabilities with Gemini 3.1 Flash Live, our highest-quality audio and voice model yet. It delivers the speed and natural rhythm required for the next generation of voice-first AI, providing intuitive information for developers, businesses and everyday users.
3.1 Flash Live is available on all Google products:
For Engineers: Critical thinking and execution
We've improved the overall quality of Flash Live 3.1, making it more reliable for developers and businesses to build voice-first agents that can complete complex tasks at scale. In ComplexFuncBench Audio, a benchmark that captures multi-step beats with various constraints, it leads with a score of 90.8% compared to our previous model.


