Qwen-Audio-3.1 Debuts with Upgraded ASR, TTS, and Realtime Capabilities, Plus Major Price Cuts

Key Info

Qwen unveiled Qwen-Audio-3.1, an upgraded audio suite including enhanced ASR, TTS, and Realtime capabilities, plus two new models: TTS-Next and ASR-Next. The lineup offers significant price cuts: TTS ~70% off, Realtime ~85% off, and ASR up to 95% off.

Highlights

• Five models form a complete audio stack: understanding, generation, interaction, and creation.
• ASR improvements include stronger multilingual and dialect recognition, and automatic removal of fillers and repetitions for cleaner transcripts.
• ASR-Next supports multi-speaker ASR with speaker labels, timestamps, and aligned transcripts, and understands emotions, ambient sounds, and machine sounds for sound captioning and event localization.