Hume AI 发布 Decision API：直接分析音频判断听者感受
精选理由
Hume AI 出了个能直接听录音回答问题的 API，判断对方是否沮丧这类情绪，测试里比单个真人听众还准。
Hume AI 推出 Hume Decision API，一个音频原生模型，可直接分析录音本身来回答问题。用户可自定义问题和选项，例如判断来电者是否听起来沮丧，模型会给出接近人类听众的答案估计。在初期测试中，该模型与评审小组平均答案的一致率为 70.7%，高于单个听众的 56.5%。
原文 · TestingCatalog
Hume AI has launched a new Hume Decision API, an audio-native model that can answer questions about a recording by analyzing the audio itself.
Users can write their own questions and answer options, such as whether a caller sounds frustrated, and receive an estimate of how human listeners would answer.
In initial tests, the model agreed with the panel's average answer 70.7% of the time, compared to 56.5% for a single listener.
