Grok Voice 3.0

xAI's speech-to-speech model in the Voice Agent API, priced at $0.08/min and scoring 86.9 on Artificial Analysis' Speech-to-Speech Index.

xAI · Generative media (image, video, audio, music, voice/avatar generation) · model

Published in Feed

Overview

xAI announced Grok Voice 3.0 on October 14, 2026 as the new model behind its Voice Agent API; the grok-voice-latest alias now points to it. xAI reports sub-one-second latency, an 86.9 score on Artificial Analysis' Speech-to-Speech Index (versus 81.3 for Grok Voice 2.0) and 98.5% on Big Bench Audio. It already powers Grok Bot voice mode, hands-free requests in Tesla vehicles, and Starlink call centers that handle about 20,000 calls a day with roughly 70% resolved without a human.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Speech-to-speech model served through the Voice Agent API
  • 86.9 on Artificial Analysis Speech-to-Speech Index; 98.5% on Big Bench Audio
  • 97.0% on Full Duplex Bench for pauses, turn-taking and interruptions
  • 94.8% task success rate and 1070 Speech Agent Arena Elo in xAI's reported comparison
  • grok-voice-latest alias upgraded automatically with no code changes

Use cases

  • Voice agents for customer-support call centers
  • In-vehicle hands-free assistants such as Tesla's voice requests
  • Real-time conversational voice mode in consumer apps

Pricing

$0.08 per minute ($4.80 per hour) in the Voice Agent API, unchanged from Grok Voice 2.0.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
14 Oct 2026
Record updated
15 Oct 2026
Record last checked
15 Oct 2026

Explore the Feed

Other entries filed under generative media (image, video, audio, music, voice/avatar generation); inclusion does not imply equivalent features.

Browse the Feed