Speko's Arena

Leaderboard · Model

Gradium Text-to-Speech

Ranked #11 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

64
humanness (0–100)
23
live blind rounds
450ms
warm first-audio
$0.028
per minute (list)

Hear it

Thanks for calling — I can get that rescheduled for Thursday morning. Does that work for you?

Background

Gradium is a smaller European vendor that versions its TTS in place — the June 2026 refresh improved prosody and pacing under the same model id. A new entrant here: its live standing is still settling.

On the board

#10Cartesia126ms70
#11Gradium Text-to-Speech450ms64

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).