Verified65% confidenceReleaseExact time
Alibaba's Qwen team released the speech recognition model Qwen-Audio-3.0-ASR-Flash.
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
8/5/2026
First Seen
Valid until: 11/3/2026
Sources
Qwen-Audio-3.0-ASR-Flash发布：医疗术语召回率达95%的语音识别新标杆
Related Claims
UnverifiedNari has launched two speech models based on Qwen3: a text-to-speech (TTS) model and an automatic speech recognition (ASR) model76% similarUnverifiedAlibaba previously released the Qwen-Audio and Qwen-VL series of models.76% similarUnverifiedAlibaba released the real-time voice interactive dialogue model Qwen-Audio-3.0-Realtime, offering Plus and Flash versions, which ranked first overall in Artificial Analysis's voice evaluation, surpassing OpenAI GPT Realtime 2.76% similarUnverifiedThe core upgrade directions of Qwen-Audio-3.0-ASR-Flash are stronger context-awareness capabilities and more accurate domain terminology recognition.75% similarUnverifiedQwen-Audio-3.1 consists of five models, covering all stages of audio processing including understanding, generation, interaction, and creation.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/687414API
curl https://kongchang.com/api/v1/knowledge/claims/687414MCP
get_claim(id=687414)