---
id: "2026-07-29-grok-voice-think-fast-2"
url: "https://postcutoff.com/e/2026-07-29-grok-voice-think-fast-2/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-07-29"
date_precision: day
category: model-release
importance: 3
confidence: high
status: [Confirmed]
sources: 4
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
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/e/2026-07-29-grok-voice-think-fast-2/

# xAI releases Grok Voice Think Fast 2.0 speech-to-speech model for voice agents

On 2026-07-29 xAI (SpaceXAI) released Grok Voice Think Fast 2.0, a reasoning speech-to-speech model for its OpenAI-Realtime-compatible Voice Agent API at $0.08/min, scoring 82.9 on the Artificial Analysis Speech-to-Speech Quality Index and cutting time to first audio to 0.70 s.

## Key facts
- Model id grok-voice-think-fast-2.0; grok-voice-latest switched to it on 2026-08-05
- Price: $0.08 per minute of audio ($4.80/hr)
- AA Speech-to-Speech Quality Index 82.9% (v1.0: 75.7%); Big Bench Audio 97.2%; Full Duplex Bench 95.1%; tau-voice Bench 56.5% (xAI)
- Time to first audio 0.70 s (from 1.25 s)
- Transcription 1.5-2x better than Deepgram Nova 3 and ElevenLabs Scribe v2 across 24 languages, ~10x in noise (xAI)
- Starlink A/B test: higher sales conversion and support containment (xAI)
- Grok voice stack also includes Grok STT/TTS APIs (2026-04-17) and Grok Voice Transcribe 2.0 (2026-09-18, $0.10/hr)

## What happened

xAI shipped the second generation of its realtime voice model, which reasons while it talks and can call web search,
X search, file search and remote MCP tools from inside a voice session. It powers Grok's voice mode, the Grok assistant
in Tesla cars and Starlink support calls, and is exposed via a WebSocket API that mirrors OpenAI's Realtime protocol.

## Why it matters

Its reported AA S2S Quality Index (82.9) put it roughly level with Google's Gemini 3.8 Live Extended Thinking (82.6,
Sept 2026) and marked xAI's push to compete on voice agents on price. Benchmarks are xAI-reported.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 90 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 29 days after its cutoff
- Gemini 4 Hydrogen (training cutoff March 2026): 120 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 59 days after its cutoff

## Sources

1. [SpaceXAI - Grok Voice Think Fast 2.0](https://x.ai/news/grok-voice-think-fast-2) (x.ai, official)
2. [xAI docs - Speech to Speech (Voice Agent API)](https://docs.x.ai/developers/model-capabilities/audio/voice-agent) (docs.x.ai, docs)
3. [SpaceXAI - Grok Voice Transcribe 2.0](https://x.ai/news/grok-voice-transcribe-2) (x.ai, official)
4. [SpaceXAI - Grok Speech to Text and Text to Speech APIs](https://x.ai/news/grok-stt-and-tts-apis) (x.ai, official)

## Changes

- 2026-09-29: Linked the Voice Agent Builder entry (2026-07-01)
- 2026-09-29 (filed): Created

## Related

- 2026-09-21: [SpaceXAI releases Grok 4.7 with a new larger base model and new safeguard stack](https://postcutoff.com/e/2026-09-21-grok-4-7/index.md)
- 2026-08-12: [SpaceXAI releases Grok 4.6, matching GPT-5.6 Sol on the AA Intelligence Index](https://postcutoff.com/e/2026-08-12-grok-4-6/index.md)
- 2026-07-01: [xAI launches Grok Voice Agent Builder, a no-code platform for phone voice agents](https://postcutoff.com/e/2026-07-01-xai-grok-voice-agent-builder/index.md)
- Models: [Grok Voice Think Fast 2.0](https://postcutoff.com/m/grok-voice-think-fast-2-0/) (`grok-voice-think-fast-2-0`)