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.
Changelog
- 2026-09-29: created
- 2026-09-29: linked the Voice Agent Builder entry (2026-07-01)
Models
- Grok Voice Think Fast 2.0 xAI · current
Related events
- SpaceXAI releases Grok 4.6, matching GPT-5.6 Sol on the AA Intelligence Index ★★★★
- SpaceXAI releases Grok 4.7 with a new larger base model and new safeguard stack ★★★★
- xAI launches Grok Voice Agent Builder, a no-code platform for phone voice agents (beta) ★★
- Artificial Analysis launches the Speech Agent Arena for speech-to-speech voice agents ★★
Sources (4)
- officialSpaceXAI - Grok Voice Think Fast 2.0
- docsxAI docs - Speech to Speech (Voice Agent API)
- officialSpaceXAI - Grok Voice Transcribe 2.0
- officialSpaceXAI - Grok Speech to Text and Text to Speech APIs
id: 2026-07-29-grok-voice-think-fast-2 · updated 2026-09-29 · open in the interactive timeline