Qwen-Audio-3.0-TTS-Plus Tops Speech Leaderboard
ArtificialAnlys · x · 2026-07-15
Alibaba's Qwen-Audio-3.0-TTS-Plus took first place on Artificial Analysis's Speech Arena 'Provider Voices' leaderboard with an Elo of 1236, slightly edging out Simba 3.2 (1234) and beating Gemini 3.1 Flash TTS and Sonic 3.5.
While this model delivers more natural pronunciation and context-aware intonation, it falls short on speed: generating 16 characters per second, notably slower than Simba 3.2 (30.2), Gemini 3.1 Flash TTS (27), and Sonic 3.5 (120).
Priced at $27.59 / 1 million characters via Alibaba Cloud Model Studio, it sits between Gemini 3.1 Flash TTS ($18.31) and Sonic 3.5 ($39.00), and is more expensive than Simba 3.2 ($10.00).
Related event: Alibaba's Qwen-Audio-3.0-TTS-Plus Tops Speech Arena(2 posts)→
More from Multimodal
- TischEins, a large Midjourney SREF library, relaunches with new design after security outage — tisch_eins · 2026-10-26
- MOSS-Image-SFT 4-step distillation tops 16.5K downloads on Hugging Face — _akhaliq · 2026-10-26
- Claude Code can now edit videos: a 10-prompt workflow from raw footage to final cut — TawohAwa · 2026-10-26
- One-sentence 3D worlds turn cinematic with CineMap and TapNow — gizakdag · 2026-10-26
- No Camera Needed: Creator Builds an Entire World in CineMap and Directs It Into Cinema — gizakdag · 2026-10-26
- Kling vs. Seedance: the Chinese AI video model rivalry — DavidmComfort · 2026-10-26