Audio / Text-to-Speech

Qwen3 TTS Flash

Text-to-speech model from Alibaba Cloud / Qwen · released Sept 2025

940Speech Arena Elo (±14)
#92-94rank range of 105
2,272blind votes
$11.03 / 1M charsAPI price
4 voicesvoices in the arena
Sept 2025release

95% confidence interval: Elo 926 – 954. 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 2025 (month precision)
Release source
Artificial Analysis Speech Arena (month precision)

More TTS models from Alibaba Cloud / Qwen