Release dates
— xAI released the real-time voice model `grok-voice-3.0`; `grok-voice-latest` now points to 3.0, which supports speech-to-speech interaction. xAI says the API and price are unchanged, and the previous `grok-voice-2.0` is deprecated. ↗
Grok Voice 3.0
xAI’s real-time speech-to-speech model, accepting text or audio and returning text and audio responses over bidirectional WebSocket.
The xAI API model ID is `grok-voice-3.0`, and `grok-voice-latest` currently points to this version. xAI says 3.0 keeps the 2.0 API, session parameters, events, and price; `grok-voice-2.0` is deprecated.
MODEL NUMBER044
- First public date
- 2026-10-14
- Organization
- SpaceXAI
- Family
- Grok
01
Specifications
Only published specifications are shown.
02
Overview
Why it mattered
Grok Voice 3.0 is a separately named voice-model version; its release moved the dynamic API alias `grok-voice-latest` to 3.0, establishing a verifiable real-time voice-model milestone.
03
Architecture & capabilities
Model capabilities
Audio generationReal-time audio
04
Release history
xAI released the real-time voice model `grok-voice-3.0`; `grok-voice-latest` now points to 3.0, which supports speech-to-speech interaction. xAI says the API and price are unchanged, and the previous `grok-voice-2.0` is deprecated.
View source05
Related models
Select a card to view the related model.
No related models recorded yet
06
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.