CodecTtsOptions
Options & Configuration · AiDotNet.TextToSpeech.CodecBased
Base configuration options for codec-based TTS models.
Inheritance: ModelOptions → TtsModelOptions → CodecTtsOptions
Known derived types: BarkOptions, SeedTTSOptions, TortoiseTTSOptions, UniAudioOptions, VoiceCloningOptions, VoiceCraftOptions, XTTSv2Options
For Beginners
These options configure the CodecTts model. Default values follow the original paper settings.
Constructors
| Constructor | Summary |
|---|---|
CodecTtsOptions() |
Initializes a new instance with default values. |
CodecTtsOptions(CodecTtsOptions other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
int CodebookSize { get; set; } |
Gets or sets the codebook vocabulary size. |
int CodecFrameRate { get; set; } |
Gets or sets the codec frame rate in Hz. |
int LLMDim { get; set; } |
Gets or sets the LLM hidden dimension. |
int MaxCodecFrames { get; set; } |
Gets or sets the maximum generation length in codec frames. |
int NumCodebooks { get; set; } |
Gets or sets the number of RVQ codebooks. |
int NumLLMLayers { get; set; } |
Gets or sets the number of LLM decoder layers. |
int SpeakerEmbeddingDim { get; set; } |
Gets or sets the speaker embedding dimension (for multi-speaker or cloning). |
string LanguageModelName { get; set; } |
Gets or sets the name of the underlying language model (e.g., “LLaMA”, “GPT-2”). |