Grok Voice 3.0 tops Artificial Analysis speech-to-speech index
AI

Grok Voice 3.0 tops Artificial Analysis speech-to-speech index

TechNews Editorial
TechNews EditorialOct 15, 2026 · 2 min read
Share

Why it matters

Artificial Analysis' tests put Grok Voice 3.0 first overall, while GPT-Live-1 led its support-call test with heavy accents and background noise.

The facts

  • Grok Voice 3.0 scored 86.9 and ranked first on Artificial Analysis' Speech-to-Speech Index.
  • GPT-Live-1 led the Tau-Voice support-call test, scoring 74.5% against Grok Voice 3.0's 71.6%.
  • Grok Voice 3.0 is available in SpaceXSI's Voice Agent API for eight cents a minute.

Advertisement

SpaceXSI, Elon Musk’s artificial intelligence company formerly known as xAI, has released Grok Voice 3.0. The speech-to-speech model powers its Voice Agent API and is aimed at businesses using voice agents for customer support and sales calls.

Independent testing firm Artificial Analysis ranked the model first on its Speech-to-Speech Index, with a score of 86.9. The index draws on reasoning tests, task success and listener votes in blind head-to-head calls. OpenAI Group PBC’s GPT-Live-1 scored 83.2 when tested with GPT-6 Astra handling its reasoning. Google LLC’s Gemini 3.8 Live scored 82.6.

Grok Voice 3.0 also scored 97% on Full Duplex Bench, which measures how naturally a model handles pauses and interruptions.

Read nextSpaceXSI bundles Grok, Cursor and X Premium in one subscription

OpenAI led one support-call test

GPT-Live-1 retained a narrow lead on Tau-Voice, a test involving support calls with heavy accents and background noise. It scored 74.5%, compared with Grok Voice 3.0’s 71.6%. SpaceXSI said its model produced its first audio about 40% faster on that test.

In Artificial Analysis’ Big Bench Audio run, a task cost about 2.5 cents on Grok Voice 3.0. The same task cost 3 cents on GPT-Live-1 and 5.5 cents on OpenAI’s GPT-Realtime-2.1.

Grok Voice 3.0 also led on accuracy in ServiceNow Inc.’s open-source EVA-Bench, scoring 74% across more than 200 enterprise scenarios. No model scored higher when accuracy and customer experience were measured together. Nitin Aggarwal, a senior director of product management at ServiceNow, said the model “pairs top accuracy with a natural, responsive conversation.”

A driver speaks to a car’s voice assistant while keeping both hands on the steering wheel and eyes on the road.
Illustration: AI & Tech News

Tesla and Starlink use Grok Voice

Tesla Inc. vehicles already account for millions of Grok Voice conversations a day. Drivers use it to check calendars and answer email. Larger requests, such as booking dinner, go through Grok Bot, whose voice mode also runs on the new model.

At Starlink, SpaceX’s satellite internet business, Grok Voice answers about 20,000 customer calls a day in several languages. SpaceXSI said roughly 70% are resolved without a person stepping in, and one in four sales calls ends in a purchase before the caller hangs up.

SpaceX acquired xAI in February. The AI unit was renamed SpaceXAI in July and took the SpaceXSI name earlier this month.

Grok Voice 3.0 is available now in the Voice Agent API for eight cents a minute, or $4.80 an hour, the same price as Grok Voice 2.0. Agents using the grok-voice-latest model alias have already been moved to the new version without changes from their developers.

Newsletter

Get the best AI & tech news daily

A concise daily digest. Unsubscribe anytime.

We use your email only to send this newsletter.

Keep reading