xAI Releases Grok Voice Think Fast 2.0
New voice model ranks high on speech benchmarks with faster response but increased audio input costs.
SpaceXAI announced Grok Voice Think Fast 2.0 as its next-generation speech-to-speech model offering gains in intelligence, transcription accuracy, and conversational ability. The High reasoning variant placed second on the Artificial Analysis Speech to Speech Index and first on Tau Voice for agentic performance. It records the lowest latency among top entries with 0.70 seconds time to first audio. Pricing for input audio rose to 4.80 dollars per hour from 3.00 dollars in the prior version, positioning it above several competitors yet below others. Official sources confirm the release and benchmark results from independent evaluations.
Announcing Grok Voice Think Fast 2.0, our next-generation voice model with improved intelligence, transcription accuracy, and conversational capabilities.


