Alibaba has released its Qwen-Audio-3.0-TTS, a new large model for speech synthesis that offers significant improvements in fine-grained control, instruction following, multilingual support, and acoustic robustness. The model comes in two versions: Qwen-Audio-3.0-TTS-Plus for high-quality generation and Fun-Realtime-TTS for real-time interaction. Qwen-Audio-3.0-TTS-Plus has achieved the top position on the Artificial Analysis global leaderboard, with its preview version also previously topping the chart. AI
IMPACT Sets a new standard for expressive and multilingual speech synthesis, potentially impacting voice acting, gaming, and real-time communication applications.
RANK_REASON New model release from a major AI lab (Alibaba) with benchmark performance claims. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
- Alibaba Group
- Artificial Analysis
- CV3-Eval
- Fun-Realtime-TTS
- Qwen-Audio-3.0-TTS
- Qwen-Audio-3.0-TTS-Plus
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
