Qwen releases Qwen-Audio-3.1 and lowers pricing across the entire Qwen-Audio voice model lineup.

TechFlow reports that on September 23, Qwen officially launched the Qwen-Audio-3.1 series of voice large models. This upgrade comprehensively evolves three core models—speech recognition (ASR), text-to-speech (TTS), and real-time voice interaction (Realtime)—while also introducing two brand-new models: the audio creation model Qwen-Audio-3.1-TTS-Next and the audio understanding model Qwen-Audio-3.1-ASR-Next.

The simultaneous release of five new voice models forms a complete audio capability stack covering "understanding, generation, interaction, and creation." To further reduce user costs, pricing across the entire Qwen-Audio voice model lineup has been lowered, with TTS reduced by approximately 70%, Realtime by about 85%, and ASR by up to 95%.