Class OpenAITranscriptionRequest.ChunkingStrategyWrapper.ServerVad

Inheritance
object
OpenAITranscriptionRequest.ChunkingStrategyWrapper.ServerVad
Inherited Members
Namespace: Glitch9.AIDevKit.OpenAI
Assembly: Glitch9.AIDevKit.Provider.OpenAI.dll
Syntax
public class OpenAITranscriptionRequest.ChunkingStrategyWrapper.ServerVad

Properties

| Edit this page View Source

PrefixPaddingMs

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

Declaration
[JsonProperty("prefix_padding_ms")]
public int? PrefixPaddingMs { get; set; }
Property Value
Type Description
int?
| Edit this page View Source

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.

Declaration
[JsonProperty("silence_duration_ms")]
public int? SilenceDurationMs { get; set; }
Property Value
Type Description
int?
| Edit this page View Source

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.

Declaration
[JsonProperty("threshold")]
public float? Threshold { get; set; }
Property Value
Type Description
float?
| Edit this page View Source

Type

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

Declaration
[JsonProperty("type")]
public string Type { get; set; }
Property Value
Type Description
string

Extension Methods