> For a complete documentation index, fetch https://docs.voximplant.ai/llms.txt

# Silero

## Classes

* [VAD](/api-reference/voxengine/silero/vad)

## Enums

* [VADEvents](/api-reference/voxengine/silero/vad-events)

## Functions

### createVAD

Creates a [Silero.VAD](/api-reference/voxengine/silero/vad) instance.

```ts
createVAD(parameters: VADParameters): Promise<Silero.VAD>
```

**Parameters**

## Types

### VADParameters

*Extends:* `_WebSocketBasedClientParameters`

[Silero.VAD](/api-reference/voxengine/silero/vad) parameters. Can be passed as arguments to the `Silero.createVAD` method.

*optional*

Optional. The duration of silence (in milliseconds) to wait for each speech segment before separating it. The default value is **300**.

*optional*

Optional. The padding to add to speech segments to avoid aggressive cutting. The default value is **0**.

*optional*

Optional. The probability threshold above which we detect speech. The default value is **0.5**.

#### Inherited fields

\_optional, inherited from *WebSocketBasedClientParameters*

Optional. Whether to enable the privacy functionality.

If privacy is enabled, the logging for the WebSocket connection is disabled.

NOTE: the default value is **false**.

\_optional, inherited from *WebSocketBasedClientParameters*

Optional. Enables statistics functionality.

\_optional, inherited from *WebSocketBasedClientParameters*

Optional. Whether to enable the tracing functionality.

If tracing is enabled, a URL to the trace file appears in the 'websocket.created' message. The file contains all sent and received WebSocket messages in the plain text format. The file is uploaded to the S3 storage.

NOTE: enable this only for diagnostic purposes. You can provide the trace file to our support team to help investigating issues.