Grok Voice 3.0

Released
2026-10-14
Last refreshed
2026-10-15
Status
Researched today
ProprietaryCommercial use: conditionalMultimodalVision
xAI releases · 18 in the last 12 months · this family litChangelog →
Specifications
Released
2026-10-14
Specialization
realtime-voice
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Pretrained
Created by
xAI

Ethical AI for universal truth-seeking

San Francisco, California, United States
Founded 2023
Website
Pricing
Audio / min
$0.080/min

List rate of 1 route · xAI Console

Providers(1)
xAI Console
View 1 provider route
Links
Website

About

Grok Voice 3.0 is xAI's speech-to-speech model for the Grok Voice Agent API, released October 14, 2026. It handles real-time spoken conversation, including pauses, turn-taking and interruptions, and xAI reports under-one-second latency. It replaced Grok Voice 2.0 behind the grok-voice-latest alias at the same price.

Providers(1)

Compare published per-minute API pricing across 1 tracked provider route.

ProviderAudio / minRoute
xAI Console$0.080/min
Serverless

Available via routers & gateways(1)

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughxAI Console

Capabilities

MultimodalAudio

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

grok-voice-latest