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

Google's Gemini 3.8 Live Extended Thinking model has taken first place on the Artificial Analysis Speech to Speech Index, while the standard version placed second in blind live human evaluations. The standard model costs $0.84 per hour of input audio, the lowest rate listed on the index.

Language: en
Time zone: America/Los_Angeles

HTML: https://didcodexreset.com/news/84742a27ff7a4982817743fb.html

Content language: en
Localization state: sameLanguage

Source: DeepLearning.AI · Published 10/7/2026, 09:06:28

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.

Tags: Google Gemini, Speech to Speech, Artificial Analysis, Voice AI

[View original post](https://x.com/DeepLearningAI/status/2107856897193697459)