Hume launches Audio Decision API, answering emotion and speaker questions directly from audio
Hume AI has released the Audio Decision API, which can answer questions directly about audio clips without prior transcription and returns a probability for each custom answer. The API incorporates sighs, laughter, hesitation, overlapping speech, and background sounds into the model input, and can process in real time or analyze hours of recordings; the company says work that previously required more than 10 models can now be done in a single call. Rohan Paul relays that one can ask "Is this caller angry?" and get a direct answer with a confidence level, and sarcastic tone will not be misjudged as positive emotion.
Why read this
AI score 53
The original text explains that the API judges emotion and speaker directly from audio, eliminating the transcription step, and can be compared against existing text-based call analysis workflows.
Topics
View original postIntroducing 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 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.
Body
A lot of the meaning in speech sits in the delivery, and models can now be asked about it directly.
The Hume Audio Decision API answers questions about a clip from the audio itself, with no transcript step, and returns a probability for each answer you define.
> puts sighs, laughter, hesitation, overlapping speech and background sounds inside the model’s input. A transcript would have reduced all of them to the same words.
> so you can ask like “Is this caller angry?”, and get a direct answer with a confidence percentage.
> Most AI judges calls by reading a text transcript, which loses tone; But this one listens to the voice itself, so a sarcastic “Oh, perfect” no longer counts as happy.
https://t.co/tewKHPdjY3