Alibaba Releases Qwen-Audio-3.0-TTS Speech Synthesis Model
Alibaba's Tongyi Lab released the Qwen-Audio-3.0-TTS speech synthesis model, featuring Flash and Plus versions. It supports 16 languages and 20 dialects, maintaining a consistent voice across languages with low latency and fine-grained style control.
2026-07-20 ~ 2026-07-21 · 5 related posts
- Episode 1: 阿里Qwen-Audio-3.0-TTS-Plus登顶语音榜(2026-07-15, 2 posts)
- Episode 2: 阿里发布 Qwen-Audio-3.0-TTS 语音合成大模型(2026-07-20, 5 posts)
- [source] Alibaba Qwen launches Qwen-Audio-3.0-TTS for real-time and premium speech — 千问大模型 · 2026-07-20
- Qwen-Audio-3.0-TTS launches with 16 languages and better voice cloning — airesearch12 · 2026-07-21
- [source] Qwen-Audio-3.0-TTS speaks 16 languages and 20 dialects from one reference voice — xiaohu · 2026-07-21