Trending storyPast story
Qwen releases Qwen-Audio-3.1 family: ASR, TTS, Realtime upgrades plus new TTS-Next and ASR-Next
1 report1 sourceupdated 7 days ago
What happened
Summary
Qwen-Audio-3.1 这次一口气放出五个模型，把之前的语音识别（ASR）、语音合成（TTS）和实时对话（Realtime）都升了级，另外新加了 TTS-Next 和 ASR-Next，分别用来做音频创作和更深层的音频理解。Realtime 模型现在能随时被打断，检测到你情绪低落时还会放慢语速、用更共情的方式回话。价格砍得挺狠：TTS 降了约七成...
Coverage
Follow the reports to see the story from different sides.
Sep 23
- AI HOT (Curated Pool)PickQwen releases Qwen-Audio-3.1 family: ASR, TTS, Realtime upgrades plus new TTS-Next and ASR-Next
Qwen dropped five audio models covering ASR, TTS, real-time conversation, and creative generation. The Realtime model supports interruption and slows down with empathetic responses when it detects low mood. Pricing is slashed: TTS ~70% off, Realtime ~85% off, ASR up to 95% off. The post doesn't disclose benchmark scores or latency numbers.