Post-Cutoff
Search For AI agents

xAIGrok Voice familyLegacySpeech and audioReleased 29 Jul 2026

Grok Voice Think Fast 2.0

xAI’s realtime voice-agent model (also used in the Grok app, Tesla vehicles and Starlink support).

Model idgrok-voice-think-fast-2.0

Price$0.08 per minute

Checked14 October 2026

Where it stands

39newer speech and audio models since its release

The 5 newest are listed. All speech and audio models

Before it from xAI
Grok Text to Speech (Grok TTS API)17 Apr 2026
After it from xAI
Grok Voice Transcribe 2.018 Sep 2026
Weights
Closed weights; access is hosted only.

How to call it

3 ways to use Grok Voice Think Fast 2.0, with the model id each provider expects.

Providers, model ids, endpoints and docs for Grok Voice Think Fast 2.0
ProviderModel idEndpointDocs
xAI API (Voice Agent / speech-to-speech, WebSocket) grok-voice-think-fast-2.0 wss://api.x.ai/v1/realtime?model=grok-voice-think-fast-2.0 docs.x.ai
xAI API (alias) grok-voice-latest docs.x.ai
Web app grok.com

Pricing

Prices for Grok Voice Think Fast 2.0
Per minute$0.08

As published: “USD per minute of audio ($4.80/hr), plus $0.004 per text input (as listed on the xAI pricing page)”.

Source: docs.x.ai, checked 14 October 2026.

Specs

Input
Audio and text
Output
Audio and text
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
29 July 2026
Status
Legacy
Type
Speech and audio

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Reasoning while speaking

    Speech-to-speech model that reasons in real time (reasoning effort ‘high’ by default, can be set to ‘none’); 97.2% Big Bench Audio, 82.9 on the Artificial Analysis Speech-to-Speech Quality Index (vs 75.7 for v1.0).

    Source: x.ai

  • Faster first audio

    Time to first audio cut from 1.25 s (v1.0) to 0.70 s; Full Duplex Bench 95.1%, tau-voice Bench 56.5% (xAI-reported).

    Source: x.ai

  • Built-in server-side tools

    Web search, X search, collections (file) search and remote MCP callable from inside a voice session, plus custom functions.

    Source: docs.x.ai

  • OpenAI Realtime-compatible protocol

    Largely compatible with the OpenAI Realtime SDK: change base URL to https://api.x.ai/v1 and the API key (minor event-name differences).

    Source: docs.x.ai

Notes

Superseded by Grok Voice 3.0 on 2026-10-14 (grok-voice-latest now points to 3.0; see entry SpaceXSI releases Grok Voice 3.0, topping Artificial Analysis’ speech-to-speech index at $0.08/min). Released 2026-07-29; grok-voice-latest switched to it on 2026-08-05. Predecessor grok-voice-think-fast-1.0 can still be pinned. 20+ languages; audio PCM (8-48 kHz), Opus 24 kHz, G.711 mu-law/A-law; server VAD, session resumption (30 min), custom cloned voices. xAI says Starlink A/B tests raised sales conversion and support containment. Benchmarks are xAI-reported.

# OpenAI Realtime-compatible WebSocket
import websockets, os
url = "wss://api.x.ai/v1/realtime?model=grok-voice-think-fast-2.0"
ws = await websockets.connect(url, additional_headers={"Authorization": f"Bearer {os.environ['XAI_API_KEY']}"})

Sources: https://x.ai/news/grok-voice-think-fast-2 · https://docs.x.ai/developers/model-capabilities/audio/voice-agent · https://docs.x.ai/developers/pricing