开源· The Decoder· 2026年6月6日· 16小时前· 1 分钟阅读
New open-source voice model listens nonstop and decides every 0.4 seconds whether to speak or stay silent
Unlike GPT-4o or Qwen3.5-Omni, Audio Interaction doesn't wait for a recording to end: it translates, transcribes, chats, and picks up everyday noises like coughing in a single stream. Code, model weights, and download i…
为何重要
开放权重的发布会对闭源定价形成压力、扩大可及性,改变整个生态「自建 vs 采购」的权衡。
摘要仅供参考,请点击来源链接查看全文。演示条目为示意。
更多资讯
模型发布8小时前
Five labs, five minds: building a multi-model finance drama on small models
模型发布8小时前
What to expect from WWDC 2026: Siri’s highly anticipated revamp and Apple Intelligence updates
政策9小时前
Sriram Krishnan is leaving his role as White House AI advisor
模型发布10小时前
The Trump administration might take an equity stake in OpenAI