Grok Voice Think Fast 2.0: xAI’s next speech-to-speech voice model
xAI released Grok Voice Think Fast 2.0, its next-generation speech-to-speech voice model with stronger speech reasoning, conversational dynamics, and tool-use reliability. Artificial Analysis scores put overall AA speech-to-speech quality at 82.9% (vs 75.7% on 1.0), Time to First Audio drops to 0.70s from 1.25s, and xAI reports 1.4× transcription accuracy gains over 1.0 plus 1.5–2.0× versus dedicated STT baselines. grok-voice-latest migrates to 2.0 on August 5 at $0.08/min of audio.




