Gemini 3.8 Live tops Artificial Analysis Speech to Speech Index at $0.84 per audio hour

According to [The Batch](https://hubs.la/Q04ztmlL0), Google's Gemini 3.8 Live speech-to-speech models process audio natively in a single system that listens, reasons, and responds without relaying through intermediate text transcription. On the Artificial Analysis Speech to Speech Index, the Gemini 3.8 Live Extended Thinking version placed first overall, while the standard model ranked second in blind live conversational evaluations judged by people.

Artificial Analysis benchmarks list the standard Gemini 3.8 Live model at $0.84 per hour of input audio, marking the lowest pricing tier on the index. Both the standard and Extended Thinking models also support direct image and video input alongside audio streams, allowing users to query the assistant regarding on-screen content.