---
updatedAt: 2025-11-13T23:35:05.000Z
---

Fetch the complete documentation index at: https://docs.thehive.ai/llms.txt. Use this file to discover all available pages before exploring further. Append .md to any documentation page URL to get its markdown version.

# Audio Detection

## Overview

Hive's AI-Generated Audio Detection API takes an audio file as input and determines whether or not that audio is AI-generated. Confidence scores are provided for each classification for easy interpretation of results. This API allows digital platforms to prevent misinformation by immediately identifying and tagging artificial audio clips.

## Response

The AI-Generated Audio Detection API has one head. This head contains two classes: `ai_generated` and `not_ai_generated`. Each class has a confidence score, which ranges from 0.0 - 1.0 and indicates how sure the model is of that class prediction.

The model breaks every input audio clip into 10 second chunks and provides a classification for each of these smaller segments. If the audio clip is less than 10 seconds in total length, it will only include one classification. Each classification also includes the timestamp of the start of that chunk.

To see an annotated example of an API response object for this model, you can visit our [API reference page](https://docs.thehive.ai/reference/ai-generated-audio-detection-1).

## Supported File Types

**Video Formats:**\
mp4\
webm\
avi\
mkv\
wmv\
mov

**Audio Formats**\
flac\
mp3\
ogg\
wav\
m4a

## Thresholds

We recommend the following thresholds for optimized model performance:

1. **General Accuracy**: 0.9
2. **Recall**: 0.5
3. **Precision**: 0.99

We recommend that you start off with these thresholds, but you should always refine these thresholds to suit your specific use case.