Interface: TextToSpeechInput

Defined in: types/tts.ts:140

Text to Speech module input definition

Extended by

• TextToSpeechStreamingInput

Properties

lang?

optional lang: TextToSpeechSupertonicLanguage

Defined in: types/tts.ts:152

supertonic only: language token for this call (e.g. 'en', 'na'). Overrides the config's lang for this synthesis without reloading the model. Defaults to the config's lang (or 'na').

---

phonemize?

optional phonemize: boolean

Defined in: types/tts.ts:144

if true (default), the input is treated as text and converted to phonemes. If false, the input should already be in IPA phonemes.

---

speed?

optional speed: number

Defined in: types/tts.ts:142

optional speed argument - the higher it is, the faster the speech becomes

---

text?

optional text: string

Defined in: types/tts.ts:141

a text to be spoken

---

totalSteps?

optional totalSteps: number

Defined in: types/tts.ts:146

supertonic only: number of flow-matching steps (default 8).