Qwen-Audio-3.1 series launches five models covering recognition, synthesis, interaction, and creation. Key updates include ASR-Next with emotion and sound understanding, TTS-Next for full audio generation, and Realtime for low-latency multi-turn dialogue. Prices drop significantly: TTS down 70%, Realtime 85%, ASR 95%. The suite supports 30 languages and 16 Chinese dialects, offering a complete audio capability stack with enhanced accuracy and accessibility.