Alibaba’s Qwen-Audio-3.0-TTS-Plus takes #1 on Artificial Analysis Speech Arena

airesearch12 · x · 2026-07-21

Alibaba’s Qwen-Audio-3.0-TTS-Plus has reached #1 on the Artificial Analysis Speech Arena leaderboard for Provider Voices, narrowly edging out Simba 3.2 and ranking ahead of Gemini 3.1 Flash TTS and Sonic 3.5.

The model is Alibaba’s latest text-to-speech release, and the post says it improves naturalness and context-appropriate intonation. Artificial Analysis’ snapshot cited an Elo score of 1,236 based on 1,305 arena appearances, just above Simba 3.2’s 1,234.

Original post →

More from Multimodal

Multimodal channel →