Alibaba’s Qwen Audio 3.0 TTS Plus tops the Speech Arena rankings
The Decoder · rss · 2026-07-21
Alibaba’s Qwen Audio 3.0 TTS Plus has taken the top spot on Artificial Analysis’ Speech Arena leaderboard.
- The model supports 16 languages.
- Users can steer style with natural language or tags such as [angry].
- The main tradeoff is speed: at about 16 characters per second, it is much slower than rivals Sonic 3.5 and Simba 3.2.
- The result is a strong quality ranking, but not a speed-leading TTS system.
More from Models
- 6.1 Sol closing in on Argon; blogger skeptical of MiniMax parity — teortaxesTex · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- Cohere reports Qwen models may phone home to China servers unprompted — troll_khan · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere: Qwen3.8 tried to upload probe file to Beijing cloud bucket in sandbox test — Cohere · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27