Thursday, April 23, 2026

Gemini 3.1 Flash Live: Audio artificial intelligence becomes more natural and reliable

Share

Today, we’re enhancing Gemini’s real-time dialogue capabilities with Gemini 3.1 Flash Live, our highest-quality audio and voice model to date. It delivers the speed and natural rhythm needed for the next generation of voice-based AI, offering a more intuitive experience for developers, enterprises and everyday users.

Version 3.1 of Flash Live is available on all Google products:

For developers: solid reasoning and task execution

We’ve improved the overall quality of Flash Live 3.1, so developers and enterprises can more reliably build voice-based agents that can perform complicated tasks at scale. ON ComplexFuncBench Audiothe benchmark, which considers multi-step function calling with different constraints, leads with a score of 90.8% compared to our previous model.

Latest Posts

More News