Class TranscriptionRequest.ChunkingStrategyWrapper.ServerVad

Namespace

Glitch9.AIDevKit.OpenAI

public class TranscriptionRequest.ChunkingStrategyWrapper.ServerVad

Inheritance

object

TranscriptionRequest.ChunkingStrategyWrapper.ServerVad

Properties

PrefixPaddingMs

Optional. Defaults to 300 Amount of audio to include before the VAD detected speech (in milliseconds).

public int? PrefixPaddingMs { get; set; }

Property Value

int?

SilenceDurationMs

Optional. Defaults to 200 Duration of silence to detect speech stop (in milliseconds). With shorter values the model will respond more quickly, but may jump in on short pauses from the user.

public int? SilenceDurationMs { get; set; }

Property Value

int?

Threshold

Optional. Defaults to 0.5 Sensitivity threshold (0.0 to 1.0) for voice activity detection. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments.

public float? Threshold { get; set; }

Property Value

float?

Type

Required. Must be set to server_vad to enable manual chunking using server side VAD.

public string Type { get; set; }

Property Value

string