Speko's Arena

Leaderboard · Model

Inworld TTS

Ranked #9 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

71
humanness (0–100)
56
live blind rounds
129ms
warm first-audio
$0.02
per minute (list)

Hear it

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

Background

Inworld built its TTS for game characters and interactive agents, where response time is everything — it posts the fastest warm first-audio on this board. TTS-2 is the current generation.

On the board

#8Rime2213ms73
#9Inworld TTS129ms71
#10Cartesia126ms70

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).