aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score47

Hume Introduces Audio Decision API for Audio Analysis in One CallMachine translation

AI introduction

Hume says its Audio Decision API can answer questions about the number of speakers, whether anyone is laughing, and whether a caller sounds frustrated. The company says tasks that previously took more than 10 models now take one call. It supports real-time audio or hours of recordings, with access available by request.

Original post · AI translation

@rohanpaul_ai
Translation · refer to the original

@hume_ai 在机器听觉方面迈出了一大步。

纯文本处理流程无法回答这些问题,因为言语内容与表达方式之间的不一致只有结合两者才能发现。

ReplyHume AI@hume_ai
Translation
隆重推出 Hume Audio Decision API。 想问什么都可以:有多少位说话者?有人在笑吗?来电者感到沮丧吗? 过去需要 10 多个模型才能完成的事,现在只需调用一次。 基于超过 1000 万条人类判断进行训练,因此它会像人类听众一样作答。 可实时处理,也可处理长达数小时的录音。 请在下方申请使用权限。
Original

Introducing the Hume Audio Decision API. Ask anything: How many speakers? Is anyone laughing? Is the caller frustrated? What used to take 10+ models is now one call. Trained on 10M+ human judgments, so it answers the way human listeners would. Realtime, or across hours of recordings. Request access below.

View this post on X ↗

Source: Rohan Paul · x.com

Products
Found an error? Send a correction