Skip to main content
Version: 0.10.0

Type Alias: KokoroTtsModel<K>

KokoroTtsModel<K> = object

Defined in: extensions/speech/tasks/kokoroTextToSpeech.ts:69

Model configuration required to instantiate the Kokoro Text-to-Speech pipeline.

Type Parameters

K

K extends PropertyKey

Voice keys record constraint (strictly inferred from voices keys).

Properties

modelPaths

readonly modelPaths: object

Defined in: extensions/speech/tasks/kokoroTextToSpeech.ts:73

Local or remote file paths to the 2 Kokoro .pte sub-models.

durationPredictor

readonly durationPredictor: string

Path to the duration predictor .pte model.

synthesizer

readonly synthesizer: string

Path to the synthesizer .pte model.


name

readonly name: "kokoro"

Defined in: extensions/speech/tasks/kokoroTextToSpeech.ts:71

Discriminates this config from the other Text-to-Speech pipelines.


phonemizer

readonly phonemizer: PhonemizerConfig

Defined in: extensions/speech/tasks/kokoroTextToSpeech.ts:80

Grapheme-to-phoneme configuration matching the model's language.


voices

readonly voices: Record<K, string>

Defined in: extensions/speech/tasks/kokoroTextToSpeech.ts:82

Map of voice names to local or remote voice .bin file paths.