Audio / Text-to-Speech

OpenVoice v2

Text-to-speech model from OpenVoice · released Apr 2024

955Speech Arena Elo (±13)
#90-91rank range of 105
3,156blind votes
$8.33 / 1M charsAPI price
—voices in the arena
Apr 2024release

95% confidence interval: Elo 942 – 968. 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
Apr 2024 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)