Audio / Text-to-Speech

Kokoro 82M v1.0

Text-to-speech model from Kokoro · released Jan 2025

1061Speech Arena Elo (±11)
#61-72rank range of 105
5,628blind votes
$0.65 / 1M charsAPI price
8 voicesvoices in the arena
Jan 2025release

95% confidence interval: Elo 1050 – 1072. Models whose intervals overlap share a rank range.

How this is measured

Speech Arena (Text-to-Speech)

Elo rating (higher is better)

Models are ranked with an Elo system derived from blind user votes: listeners hear two speech samples generated from the same text and pick the one that sounds more natural. The provider-voice leaderboard uses each provider's own native voices. Each result is reported with a 95% interval and the number of votes (samples).

Release & sources

Release
Jan 2025 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)