Audio / Text-to-Speech

OpenAudio S1

Text-to-speech model from Fish Audio · released Jun 2025

1089Speech Arena Elo (±11)
#48-56rank range of 105
4,863blind votes
$15.00 / 1M charsAPI price
8 voicesvoices in the arena
Jun 2025release

95% confidence interval: Elo 1078 – 1100. 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
Jun 2025 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)

More TTS models from Fish Audio