Leaderboard · Model
xAI Grok Text-to-Speech
Ranked #2 of 11 models by blind A/B votes against a real human recording. Humanness 100 means listeners can no longer tell it from the person.
Standings as of August 31, 2026 · refreshed every 5 minutes
Hear it
“Thanks for calling — I can get that rescheduled for Thursday morning. Does that work for you?”
Background
xAI's text-to-speech is the voice behind Grok Voice across the mobile apps and Tesla integrations — a stack xAI built in house. It ranks #1 on Vapi's Humanness Index and trades the top spots here as live votes accumulate.
On the board
Live results — the numbers move as votes land. Latency is measured at the Speko gateway (warm first-audio, n=30); price is the provider's published rate. Method details on the methodology page; raw standings as open data (CC BY 4.0).