Google has released Gemini 3.1 Flash Live, a high-quality audio and voice model designed to accelerate the development of next-generation voice-first AI experiences.
Gemini 3.1 Flash Live represents a significant advancement in Google’s real-time dialogue capabilities, focusing on speed and natural rhythm to create a more intuitive experience for users. This model is specifically targeted at developers, enterprises, and everyday users seeking to leverage voice-based AI. Key improvements include robust reasoning and task execution, enabling developers to build reliable voice-first agents capable of handling complex tasks at scale. The model's performance has been validated through benchmarks like ComplexFuncBench Audio, achieving a leading score of 90.8% on multi-step function calling with various constraints. This enhanced quality makes 3.1 Flash Live a particularly valuable tool for enterprise applications. DATA: 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. 3.1 Flash Live is available across Google products: For developers: Robust reasoning and task execution 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.
Tags:
Google