Audio / Text-to-Speech

Qwen-Audio-3.1-TTS-Plus

Text-to-speech model from Alibaba Cloud / Qwen · released Sept 2026

1300Speech Arena Elo (±14)
#3-5rank range of 105
2,490blind votes
$19.31 / 1M charsAPI price
8 voicesvoices in the arena
Sept 2026release

95% confidence interval: Elo 1286 – 1314. 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
Sept 2026 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)

More TTS models from Alibaba Cloud / Qwen