Skip to content
AI IntelligenceSep 24, 2026AI Intelligence
Article

Alibaba releases Qwen-Audio-3.1 suite with five new models

Alibaba's Qwen team has launched Qwen-Audio-3.1, a suite of five models for speech recognition, text-to-speech, and real-time interaction. The ASR model improves multilingual and dialect recognition, while the ASR-Next model adds multi-speaker identification with timestamps and emotion detection.

Frontier EditorialSource: The Decoder
01

Source Brief

Alibaba releases Qwen-Audio-3.1 suite with five new models: Alibaba's Qwen team has launched Qwen-Audio-3.1, a suite of five models for speech recognition, text-to-speech, and real-time interaction. The ASR model improves multilingual and dialect recognition, while the ASR-Next model adds multi-speaker identification with timestamps and emotion detection.