Audio / Text-to-Speech

Step TTS 2 (Mar 2026)

Text-to-speech model from StepFun · released Feb 2026

1136Speech Arena Elo (±11)
#35-38rank range of 105
3,137blind votes
$40.00 / 1M charsAPI price
2 voicesvoices in the arena
Feb 2026release

95% confidence interval: Elo 1125 – 1147. 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
Feb 2026 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)

More TTS models from StepFun