Qwen Releases Qwen-Audio-3.1, Cuts Prices Across Entire Qwen-Audio Speech Model Line

Beating AI News Flash: Qwen officially releases the Qwen-Audio-3.1 series of large speech models. This upgrade not only comprehensively evolves the three core models—Automatic Speech Recognition (ASR), Text-to-Speech (TTS), and Realtime voice interaction—but also重磅 launches the all-new audio creation model Qwen-Audio-3.1-TTS-Next and audio understanding model Qwen-Audio-3.1-ASR-Next. Five all-new speech models are launched simultaneously, forming a complete audio capability stack covering "understanding-generation-interaction-creation."

To further reduce user costs, prices for all Qwen-Audio speech models have been lowered, with TTS reduced by about 70%, Realtime by about 85%, and ASR by as much as 95%.