Search Results for

    Show / Hide Table of Contents

    Class SpeechGenerationRequestBase<TSelf, TPrompt, TConfig>

    Inheritance
    object
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>
    StreamingGenerativeRequest<TSelf, TPrompt, IAudioAsset, Delta<IAudioChunk>, TConfig>
    GenerativeAudioRequest<TSelf, TPrompt, TConfig>
    SpeechGenerationRequestBase<TSelf, TPrompt, TConfig>
    SpeechGenerationRequest
    VoiceChangeRequest
    Implements
    IGenerativeRequest
    IStreamingGenerativeRequest<Delta<IAudioChunk>, IAudioAsset>
    Inherited Members
    GenerativeAudioRequest<TSelf, TPrompt, TConfig>.ResponseType
    GenerativeAudioRequest<TSelf, TPrompt, TConfig>.FileNameKey
    GenerativeAudioRequest<TSelf, TPrompt, TConfig>.OutputFormat
    GenerativeAudioRequest<TSelf, TPrompt, TConfig>.SetEncoding(AudioEncoding)
    GenerativeAudioRequest<TSelf, TPrompt, TConfig>.SetElevenLabsFormat(ElevenLabsTypes.OutputFormat)
    StreamingGenerativeRequest<TSelf, TPrompt, IAudioAsset, Delta<IAudioChunk>, TConfig>.StreamAsync(CancellationToken)
    StreamingGenerativeRequest<TSelf, TPrompt, IAudioAsset, Delta<IAudioChunk>, TConfig>.StreamAsyncInternal()
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.FileNameKey
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.FallbackModel
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.ModelType
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.Api
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.Prompt
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.Model
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.N
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.Seed
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.MeasureLatency
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.OnLatencyMeasured
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.RequestedAt
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.RecordOptions
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.RecordedContext
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetModel(Api, string)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetModel(ModelBase)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetCount(int)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetN(int)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetSeed(long)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetRecordOptions(bool?, bool?, string, string, GenerationRecord, RecordMerger, Action<GenerationRecord>)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetRecordOptions(GenerationRecordOptions)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetMeasureLatency(Action<double>)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetMeasureLatency(bool, Action<double>)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.SetPlaygroundSettings(string, string, string, bool, Action<double>, Action<GenerationRecord>)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.ExecuteAsync(CancellationToken)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.ExecuteAsyncT<T>(CancellationToken)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.ProcessPostRequestTasks<T>(Generated<T>)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.ProcessPostRequestTasks(IResult)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.GetPrompt()
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.GetPromptStringToRecord()
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.ResolveDownloadOptions(DownloadOptions)
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.ValidateRequest()
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.GenerateDefaultFileName()
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.PrepareRequestAsync()
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.m_Api
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.Api
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.RequestType
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.HttpOptions
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.DownloadOptions
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.Sender
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.LogOptions
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.ContentType
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.ResponseType
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.IsCanceled
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.Stream
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SafetyIdentifier
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.ServiceTier
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.Metadata
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.ProviderOptions
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.Options
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetSender(string)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetLogOptions(CurlLogOptions)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetOutputPath(string)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetOutputPath(string, string)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetOutputDirectory(string)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetDownloadOptions(DownloadOptions)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetRequestMimeType(MimeType)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetResponseMimeType(MimeType)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetStream(bool)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetMetadata(ServerDictionary)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetSafetyIdentifier(string)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetProviderOptions(TConfig)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetSpecificOptions(TConfig)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.ValidateRequest()
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.GetConfig<T>()
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.SetApi(Api)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.ExecuteAsync(CancellationToken)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.Cancel()
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.ExecuteAsyncInternal()
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.ResolveDownloadOptions(DownloadOptions)
    UnifiedApiRequestBase<TSelf, Generated<IAudioAsset>, TConfig>.GenerateDefaultFileName()
    object.Equals(object)
    object.Equals(object, object)
    object.GetHashCode()
    object.GetType()
    object.MemberwiseClone()
    object.ReferenceEquals(object, object)
    object.ToString()
    Namespace: Glitch9.AIDevKit
    Assembly: Glitch9.AIDevKit.dll
    Syntax
    public abstract class SpeechGenerationRequestBase<TSelf, TPrompt, TConfig> : GenerativeAudioRequest<TSelf, TPrompt, TConfig>, IGenerativeRequest, IStreamingGenerativeRequest<Delta<IAudioChunk>, IAudioAsset> where TSelf : SpeechGenerationRequestBase<TSelf, TPrompt, TConfig> where TPrompt : IPrompt where TConfig : IProviderRequestOptions
    Type Parameters
    Name Description
    TSelf
    TPrompt
    TConfig

    Constructors

    | Edit this page View Source

    SpeechGenerationRequestBase(TPrompt)

    Declaration
    protected SpeechGenerationRequestBase(TPrompt prompt)
    Parameters
    Type Name Description
    TPrompt prompt

    Properties

    | Edit this page View Source

    SimilarityBoost

    Only applicable when using ElevenLabs API. Optional. Determines how closely the AI should adhere to the original voice when attempting to replicate it.

    Declaration
    public double? SimilarityBoost { get; set; }
    Property Value
    Type Description
    double?
    | Edit this page View Source

    Stability

    Only applicable when using ElevenLabs API. Optional. Determines how stable the voice is and the randomness between each generation. Lower values introduce broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion.

    Declaration
    public double? Stability { get; set; }
    Property Value
    Type Description
    double?
    | Edit this page View Source

    Style

    Only applicable when using ElevenLabs API. Optional. Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. This setting consumes additional computational resources and might increase latency if set to anything other than 0.

    Declaration
    public double? Style { get; set; }
    Property Value
    Type Description
    double?
    | Edit this page View Source

    UseSpeakerBoost

    Only applicable when using ElevenLabs API. Optional. This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency.

    Declaration
    public bool? UseSpeakerBoost { get; set; }
    Property Value
    Type Description
    bool?
    | Edit this page View Source

    UseStyleExaggeration

    Only applicable when using ElevenLabs API. Optional. The use of style exaggeration in the voice output.

    Declaration
    public bool? UseStyleExaggeration { get; set; }
    Property Value
    Type Description
    bool?
    | Edit this page View Source

    Voice

    Declaration
    public string Voice { get; set; }
    Property Value
    Type Description
    string

    Methods

    | Edit this page View Source

    SetVoice(Api, string)

    Sets the voice preset name (string-based, for future compatibility).

    Declaration
    public TSelf SetVoice(Api api, string voice)
    Parameters
    Type Name Description
    Api api
    string voice
    Returns
    Type Description
    TSelf
    | Edit this page View Source

    SetVoice(Voice)

    Declaration
    public TSelf SetVoice(Voice voice)
    Parameters
    Type Name Description
    Voice voice
    Returns
    Type Description
    TSelf
    | Edit this page View Source

    ValidateRequest()

    Validates the request before execution. Override in derived classes to implement request validation logic.

    Declaration
    protected override void ValidateRequest()
    Overrides
    GenerativeRequest<TSelf, TPrompt, IAudioAsset, TConfig>.ValidateRequest()

    Implements

    IGenerativeRequest
    IStreamingGenerativeRequest<TEvent, TAsset>

    Extension Methods

    ArrayExtensions.ToArrayOrEmpty<T>(T)
    ArrayExtensions.ToArrayOrNull<T>(T)
    EventExtensions.ToDelta<T>(T, string, int, string, bool)
    EventExtensions.ToDone<T>(T, string, int, string)
    EventExtensions.ToEvent<T>(T)
    EventExtensions.UpcastDelta<T1, T2>(T1, string, int, string, bool)
    FallbackExtensions.IsOr<TParent, TChild>(TParent, TChild)
    ResponseCastingExtensions.GetResult<T>(T)
    SystemExtensions.GetName(object)
    • Edit this page
    • View Source
    In this article
    Back to top AI DevKit Documentation