Alibaba Qwen releases Qwen-Audio-3.0-TTS, tops TTS leaderboard

通义千问发布Qwen-Audio-3.0-TTS，登顶TTS排行榜

Alibaba Qwen dropped two TTS variants: Flash for real-time interaction and Plus for high-quality generation. The model supports fine-grained inline tags like 【whisper】 and 【angry】, natural-language style control, 16 languages, and up to 3 minutes of audio per generation. It currently ranks #1 on the Artificial Analysis TTS leaderboard. The post doesn't disclose parameter counts, latency figures, or pricing.

Why it matters: Alibaba Qwen drops a TTS model with clear Flash/Plus tiering and tops the Artificial Analysis leaderboard — a solid signal. Score held at 78 because the post doesn't disclose param count, latency numbers, or API pricing, which are the numbers builders actually need. Domestic f...