Not established from the available sources.
XAI · MODEL RELEASE TRACKER
Grok Voice Think Fast 2.0
Grok Voice Think Fast 2.0 is xAI's next-generation speech-to-speech voice model announced on 2026-09-16. It claims improved intelligence, transcription accuracy, conversational ability, and tool-use reliability versus its predecessor, with specific benchmarked gains against Deepgram Nova 3 and ElevenLabs Scribe v2 and strong robustness in noisy and telephony-compressed settings.CURRENT SNAPSHOT2/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
ModalitySpeech-to-speech (voice) model
Transcription accuracy benchmarksEvaluated on thousands of short phrases in 24 languages: 1.5–2.0× improvement vs Deepgram Nova 3 and ElevenLabs Scribe v2; 1.4× improvement vs Grok Voice Think Fast 1.0; gap grows to ~10× in noisy settings.
Not established from the available sources.
VERIFIABLE FACTS
Every value stays attached to a source and date.
RELEASE · Announcement dateDEVELOPER CLAIM
Announced on 2026-09-16 in an xAI blog post
MODALITIES · ModalityDEVELOPER CLAIM
Speech-to-speech (voice) model
CAPABILITIES · Capabilities (summary)DEVELOPER CLAIM
Reported improvements in intelligence, transcription accuracy, conversational ability, and tool-use reliability compared with its predecessor.
CAPABILITIES · Reasoning while speakingDEVELOPER CLAIM
Model
BENCHMARKS · Transcription accuracy benchmarksDEVELOPER CLAIM
Evaluated on thousands of short phrases in 24 languages: 1.5–2.0× improvement vs Deepgram Nova 3 and ElevenLabs Scribe v2; 1.4× improvement vs Grok Voice Think Fast 1.0; gap grows to ~10× in noisy settings.
CAPABILITIES · Robustness in real-world conditionsDEVELOPER CLAIM
Designed to perform well in real-world settings with substantial background noise and telephony compression.
WHAT CHANGED