# Hume releases an audio decision model that answers questions from raw sound

> Original title: This is a new decision model for audio input:

- Source: Santiago
- Published: 2026-11-02T16:29:00.000Z
- Bad Influence: https://badinfluence.news/items/njfin3ij4maf14dbovotcz3xi
- Original: https://x.com/svpino/status/2117292904045781358

## Summary

Hume's new Audio Decision API takes audio and a list of questions and returns answers with confidence scores, without a transcript. According to Santiago, the model can answer from tone, hesitation, and laughter, clues a transcript would miss. Hume says the model replaces more than 10 separate models with one call and was trained on 10M+ human judgments.

## Post

This is a new decision model for audio input:

• You provide the audio
• You provide a list of questions
• Model outputs answers + confidence scores

The model analyzes the audio directly (no transcript needed).

Something really cool is the model's ability to answer questions based on tone, hesitation, laughter, and other audio clues that wouldn't be in a transcript.

## Quoted post @hume_ai

> 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.

https://x.com/hume_ai/status/2117285608745820372