As of: 2026-10-14 22:23 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/grok-voice-3-0/

# Grok Voice 3.0

SpaceXSI, Grok Voice family. Status: current. Type: speech and audio. Released: 2026-10-14.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| xAI / SpaceXSI API (Voice Agent, speech-to-speech) | `grok-voice-latest` |  | https://docs.x.ai/developers/model-capabilities/audio/voice-agent |

## Pricing

- Per minute: $0.08
- Unit as published: USD per minute of audio ($4.80/hr), same as Grok Voice 2.0
- Source: https://x.ai/news/grok-voice-3
- Last checked: 2026-10-14

## Specs

- Input: audio, text
- Output: audio, text
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- No newer speech and audio model in the registry yet.
- Closed weights; access is hosted only.

## What stands out

- Top Artificial Analysis speech-to-speech score: 86.9 on the Artificial Analysis Speech-to-Speech Index (Oct 13, 2026), above GPT-Live-1 (83.2) and Gemini 3.8 Live (82.6); Big Bench Audio 98.5%, τ-Voice 71.6% (vendor-reported). Source: https://x.ai/news/grok-voice-3

## Notes

Released 2026-10-14; the grok-voice-latest alias moved to it automatically. No pinned versioned id stated on the launch page. Under-1-second latency claimed.


Model page: https://postcutoff.com/m/grok-voice-3-0/