[Qianwen Large Model Releases Qwen-Audio-3.1 and Lowers the Price of Qwen-Audio's Full Line of Voice Models] On September 23, Qianwen officially released the Qwen-Audio-3.1 series of large voice models. This upgrade not only comprehensively evolves the three core models of speech recognition (ASR), speech synthesis (TTS) and real-time speech interaction (Realtime), but also launches a new audio creation model Qwen-Audio-3.1-TTS-Next and audio understanding model Qwen-Audio-3.1-ASR-Next. Five new speech models were launched at the same time, forming a complete audio capability stack covering "understanding-generation-interaction-creation". In order to further reduce user costs, the prices of Qwen-Audio's entire line of voice models have been reduced, with TTS prices reduced by about 70%, Realtime prices dropped by about 85%, and ASR prices dropped by 95%.