Hume Audio Decision API supports asking questions directly about audio

Nov 3

1. 02:58

   Alvaro CintasRelated discussion

   Alvaro Cintas joined this discussion ↗

   This post contributes to heat; it is not a formal report or confirmed fact.

2. 01:45

   Testing Catalog

   Hume AI releases the Hume Decision API, using an audio-native model to answer questions about recordings

   Hume AI launches the Hume Decision API, an audio-native model that can directly analyze the recording itself to answer questions about the recording. Users can customize questions and options, for example, determining whether a caller appears frustrated, and obtain an estimate of how human listeners would answer. In preliminary tests, the model's agreement rate with the review panel's average answers was 70.7%, compared with 56.5% for an individual human listener.

   Expand summary
3. 01:17

   HaiderRelated discussion

   Haider joined this discussion ↗

   This post contributes to heat; it is not a formal report or confirmed fact.

4. 00:56

   Rohan Paul

   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.

   Expand summary