Qwen launched the Qwen-Audio-3.1 series, featuring ASR, ASR-Next, TTS, TTS-Next, and Realtime models. Key upgrades include multi-language and dialect support, emotion recognition, and full-duplex interaction. Significant price cuts include 70% for TTS, 85% for Realtime, and up to 95% for ASR. The models are now available on the Qwen AI platform, with the ASR-Next API rolling out soon. These advancements position audio as a natural interface for human-computer interaction, integrating with smart hardware and AI agents.