Audio model

Grok Voice Think Fast 2.0

Grok Voice Think Fast 2.0 is a speech-to-speech voice model built for real-time conversational voice agents. It reasons while speaking, delivering sub-second response times without sacrificing intelligence. The model handles noisy audio and varied accents across 25+ languages, executes tool calls mid-conversation, and follows multi-step workflows for tasks like customer support and appointment scheduling.

Type
Audio
Weights
Closed