Qwen-Audio-3.0-TTS speaks 16 languages and 20 dialects from one reference voice
xiaohu · x · 2026-07-21
Qwen-Audio-3.0-TTS supports 16 languages and 20 dialects from one reference voice
Alibaba’s Tongyi team released Qwen-Audio-3.0-TTS, a voice model that can speak 16 languages and 20 dialects from a single reference sample.
- First-token latency is said to be around 300 ms.
- The same reference voice can be carried across all 16 languages without obvious timbre drift.
- On CV3-Eval, the model reportedly ranked first in speaker similarity across all 16 languages, with a Plus average score of 82.75/100.
Related event: Alibaba Releases Qwen-Audio-3.0-TTS Voice Synthesis Model(5 posts)→
More from Multimodal
- Hi3D V1.0 open-sourced with 2M training assets and 90% slicing success rate — kimmonismus · 2026-10-26
- Claude Can Replace Your YouTube Thumbnail Designer in 10 Minutes — thedankoe · 2026-10-26
- Multimodal AI Is Not Useless: A Practitioner Pushes Back on Growing Skepticism — thoma_gu · 2026-10-26
- One prompt, full Blender animation: dev says he never touched Blender once — iamfakhrealam · 2026-10-26
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26
- LichtFeld Studio v0.5.4.3 ships community-built SteadySplats, POPSpa and Voxelization — janusch_patas · 2026-10-26