Leaderboard · Model
MiniMax Speech
Ranked #1 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
MiniMax is a Shanghai-based AI lab; its Speech 2.6 HD model is the high-fidelity tier of the T2A family, with emotion control and inline pause markup. It arrived near the top of Vapi's Humanness Index and currently leads this board's live votes.
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).