---
title: "VAD Elastic"
slug: "vad-elastic"
updated: 2026-03-27T11:55:41Z
published: 2026-03-27T11:55:41Z
---

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

# VAD Elastic

## Vad Elastic

### Supported Sample Rates

| Engines | 8 kHz | 16 kHz | 32 kHz | 48 kHz |
| --- | --- | --- | --- | --- |
| VadLite2 | ✔️ | ✔️ | ✔️ | ✔️ |
| Silero | ✔️ | ✔️ |  |  |

### Parameters

| name | description | default |
| --- | --- | --- |
| Engine Type | Underlying VAD Engine | VadLite2 |
| Silence Trigger Duration (ms) | The amount of silence in milliseconds for VAD to expect in order to decide that the speech has actually ended | 600 |
| Early Silence Trigger Duration (ms) | The amount of silence in milliseconds For VAD to expect in order trigger *Early Speech Ended*. Recommended 200 msec | -1 (disabled) |
| Pre-Speech Buffer Length (ms) | After start of speech is detected VAD rewinds and takes a little more data before the detected beginning, just in case a low energy voice happens to be there. This duration is determined by pre-speech-buffer-msec | 300 |
| Post-Speech Buffer Length (ms) | After the end of speech is detected VAD takes a little more data after the detected end just in case a low energy voice happens to be there. This duration is determined by post-speech-buffer-msec. | 300 |
| Sensitivity | The range is 0.0-1.0 inclusive, Determines the threshold of Speech Possibility. Speech Started event triggers when Speech Possibility > Sensitivity. | 0.6 |
| Max Speech Duration (ms) | If the speech does not end after this duration it will be ended by VAD. This will be treated as a normal end of speech, and an appropriate speech-ended event will be generated. Exceeding this timeout will not generate an error. | -1 |
| Max Speech Duration Graceful End (%) | Specify the last % part of Max Speech Duration, engine becomes more sensitive to silence. It's active only if Max Speech Duration is set. | 20 |

### Inputs

#### Audio

Accepts audio from a single channel.

#### Events

none

### Outputs

#### Audio

After removing the silences in the input audio the remaining data is sent to output.

#### Events

| name | description |
| --- | --- |
| [Speech Started](/v1/docs/events#speech-started) | Raised once at the beginning of each piece of actual audio fragment. |
| [Early Speech Ended](/v1/docs/events#early-speech-ended) | Raised when VAD Engine detects Early Silence. Can be raised multiple times for each utterance. |
| [Speech Ended](/v1/docs/events#speech-ended) | Raised once at the end of each piece of actual audio fragment. |

### Remarks

### Project Structure

A simple project can be built as such:

![image.png](https://cdn.document360.io/9bca2910-6a3b-4224-9470-43f91f9a6d57/Images/Documentation/image-G0KOQ0Y8.png)

Important Note

Make sure that both the `Audio` output and the `Event` output is connected to the receiving nodes. Otherwise, the following nodes will not know when the speech starts and ends.

#### Supported Flow Types

Batch, Stream

### Release History

****v4.10.0****

      
          

- Added Early Silence support.
- Changed Silence Trigger Duration default value to 600 ms from 400 ms.

        
  

****v4.2.0****

      
          

- Introduced node.