Table of Contents

Class AutomaticActivityDetection

Namespace
GenerativeAI.Types
Assembly
GenerativeAI.dll

Configures automatic detection of activity.

public class AutomaticActivityDetection
Inheritance
AutomaticActivityDetection
Inherited Members
Extension Methods

Properties

Disabled

If enabled, detected voice and text input count as activity. If disabled, the client must send activity signals.

[JsonPropertyName("disabled")]
public bool? Disabled { get; set; }

Property Value

bool?

EndOfSpeechSensitivity

Determines how likely detected speech is ended.

[JsonPropertyName("endOfSpeechSensitivity")]
public EndSensitivity? EndOfSpeechSensitivity { get; set; }

Property Value

EndSensitivity?

PrefixPaddingMs

The required duration of detected speech (in milliseconds) before start-of-speech is committed. The lower this value the more sensitive the start-of-speech detection is and the shorter speech can be recognized. However, this also increases the probability of false positives.

[JsonPropertyName("prefixPaddingMs")]
public int? PrefixPaddingMs { get; set; }

Property Value

int?

SilenceDurationMs

The required duration of detected non-speech (e.g. silence, in milliseconds) before end-of-speech is committed. The larger this value, the longer speech gaps can be without interrupting the user's activity but this will increase the model's latency.

[JsonPropertyName("silenceDurationMs")]
public int? SilenceDurationMs { get; set; }

Property Value

int?

StartOfSpeechSensitivity

Determines how likely speech is to be detected.

[JsonPropertyName("startOfSpeechSensitivity")]
public StartSensitivity? StartOfSpeechSensitivity { get; set; }

Property Value

StartSensitivity?