Alibaba Cloud Model Studio - Qwen-Audio-3.1-TTS-Flash Real-Time Speech Synthesis Large Model Published
Sep 18 2026
Alibaba Cloud Model StudioContent
Applicable customers: All customers. New Feature/Specification: Qwen-Audio-3.1-TTS-Flash is a high-performance speech synthesis large model for real-time interactive scenarios. It supports multiple languages and dialects. The model features free-style instruction following and fine-grained label control capabilities, enabling more flexible control over expressions such as emotion, tone, role, speech rate, and volume. Additionally, the model demonstrates greater robustness under complex acoustic conditions such as noise and reverberation in voice cloning scenarios, improving sound quality, definition, and overall expressiveness. The Flash version focuses on optimizing the real-time synthesis experience and is suitable for low-latency interaction scenarios such as voice assistants, real-time conversations, and intelligent customer service. ▸ Try Now.