Alibaba has released its Qwen-Audio-3.0-TTS large language model for speech synthesis, featuring improvements in control, instruction following, multilingual support, and robustness. The model includes a real-time version, Fun-Realtime-TTS, and a high-quality version, Qwen-Audio-3.0-TTS-Plus, which has topped the Artificial Analysis leaderboard. Separately, Shanghai aims to develop 500,000 kilowatts of green electricity direct connection projects by 2030 to support economic green transformation. AI
IMPACT Enhances speech synthesis capabilities with improved control and real-time performance, potentially impacting voice applications and accessibility.
RANK_REASON The cluster reports on a new speech synthesis model release and infrastructure development plans, which falls under tool and infrastructure categories.
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
