Type Alias: SupertonicTtsModel<K>

SupertonicTtsModel<K> = object

Defined in: extensions/speech/tasks/supertonicTextToSpeech.ts:74

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

Type Parameters

K

K extends PropertyKey

Voice style keys record constraint (strictly inferred from voiceStyles keys).

Properties

modelPaths

readonly modelPaths: object

Defined in: extensions/speech/tasks/supertonicTextToSpeech.ts:78

Local or remote file paths to the 4 Supertonic .pte sub-models.

durationPredictor

readonly durationPredictor: string

Path to the duration predictor .pte model.

textEncoder

readonly textEncoder: string

Path to the text encoder .pte model.

vectorEstimator

readonly vectorEstimator: string

Path to the vector estimator .pte model.

vocoder

readonly vocoder: string

Path to the vocoder .pte model.

---

name

readonly name: "supertonic"

Defined in: extensions/speech/tasks/supertonicTextToSpeech.ts:76

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

---

unicodeIndexerPath

readonly unicodeIndexerPath: string

Defined in: extensions/speech/tasks/supertonicTextToSpeech.ts:89

Local or remote path to the unicode_indexer.json character mapping file.

---

voiceStyles

readonly voiceStyles: Record<K, string>

Defined in: extensions/speech/tasks/supertonicTextToSpeech.ts:91

Map of voice style names to local or remote JSON file paths.