Grok Voice 3.0: xAI's speech-to-speech model for voice agents

xAI has released Grok Voice 3.0, a speech-to-speech model aimed at voice agents such as customer support callers. xAI calls it the world's most intelligent speech-to-speech model and says it sets a record for resolving support calls.

According to xAI, the model has latency under one second and costs less than other frontier models. It cites Artificial Analysis testing, where Grok Voice 3.0 ranks first on the Speech-to-Speech Index with 86.9, against 81.3 for Grok Voice 2.0, 83.2 for GPT-Live-1 (Astra, Medium) and 82.6 for Gemini 3.8 Live. It also reports 97% on Full Duplex Bench, which measures handling of pauses and interruptions.

Grok Voice 3.0 is available now in the Voice Agent API at $0.08 per minute ($4.80 per hour), the same price as Grok Voice 2.0. Agents using grok-voice-latest were switched over automatically. xAI says the model handles millions of conversations a day in Tesla vehicles and powers Grok Bot's voice mode.

xAI also says Starlink call centers use it for 20,000 customer calls a day, with roughly 70% resolved without a human. On ServiceNow's EVA-Bench, xAI says it scored the highest accuracy at 74%. It succeeds Grok Voice 2.0 at an unchanged price.