> ## Documentation Index
> Fetch the complete documentation index at: https://docs.inworld.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Inworld VAD Module

[Overview](../overview) > Inworld VAD Module

**Class:** `InworldVADModule` | **Inherits from:** `InworldFrameworkModule`

Module for Voice Activity Detection (VAD) within the Inworld framework. Analyzes audio input to determine when speech is present versus silence or background noise. Used for optimizing speech processing by filtering out non-speech audio segments.

## Methods

* [DetectVoiceActivity](#detectvoiceactivity)

## Reference

### DetectVoiceActivity

Detects voice activity in the provided audio chunk.
Analyzes the audio data to determine if speech is present based on the configured threshold.

#### Parameters

| Parameter  | Type         | Description                                   |
| ---------- | ------------ | --------------------------------------------- |
| audioChunk | `AudioChunk` | The audio data to analyze for voice activity. |

#### Returns

**Type:** `int`

**Description:** 1 if voice activity is detected, 0 if no voice activity, or -1 if detection failed.

***

## Serialized Fields

The following fields are configurable in the Unity Inspector:

* **m\_Threshold** (`float`) - Voice activity detection threshold (default: 0.3, range: 0-1)

## Important Notes

The VAD module only supports local model execution.

***