Trending storyDeveloping

Artificial Analysis ranks Grok Voice 3.0 at 0.81s time to first audio on Big Bench Audio

1 article1 sourcesince Oct 14Last article 1h ago · Oct 14, 1:26 PM ET

Overview

AISummary of 1 article

Artificial Analysis reports that Grok Voice 3.0 averages 0.81 seconds to first audio on the Big Bench Audio benchmark.

The firm says that is about 40% faster than GPT-Live-1 (Astra, medium) at 1.34 seconds and Gemini 3.8 Live Extended Thinking (High) at 1.35 seconds, the next two models in its Speech to Speech Index.

Within the index's top five, only Grok Voice 3.0 and Grok Voice 2.0 score under 1 second. Grok Voice 2.0 averages 0.70 seconds, faster than Grok Voice 3.0.

Written by AI from the articles below · updated Oct 14, 1:37 PM ET

Check the sources:

Latest developmentOct 14, 1:26 PM ET

Grok Voice 3.0 posts 0.81s time to first audio on Big Bench Audio

Article timeline

The articles in this story. Times are ET.

Oct 14

1:26 PM
Artificial Analysis@ArtificialAnlysOfficial
Grok Voice 3.0 posts 0.81s time to first audio on Big Bench Audio
AIArtificial Analysis says Grok Voice 3.0 averages 0.81 seconds to first audio on the Big Bench Audio benchmark. That is about 40% faster than GPT-Live-1 (Astra, medium) at 1.34 seconds and Gemini 3.8 Live Extended Thinking (High) at 1.35 seconds, the next two models in its Speech to Speech Index. Only Grok Voice 3.0 and Grok Voice 2.0, which averages 0.70 seconds, score under 1 second among the index's top five.

Heat trend

Not enough continuous observations to show a trend yet.