Grok Voice Think Fast 2.0 now available on AI Gateway
- Source
- vercel.com
- Author
- Kevin Dawkins
- Date

If you're building voice agents, the parallel-reasoning-while-speaking design means you can get tool calls fired mid-sentence without the usual think-then-speak latency penalty, and improved telephony-grade transcription makes it viable for phone-channel deployments. Availability through Vercel's AI Gateway realtime API means you can swap it into an existing realtime stack without a new provider integration.
“The model reasons in parallel with speech, so it can think through a query while talking without adding latency.”
“It has also been trained to use fewer reasoning tokens than before, so tool calls fire sooner, often before the end of the agent's first sentence.”
“Transcription holds up in real-world conditions, including background noise and telephony compression.”
Checking sign-in…
Loading comments…






