Interface TTSOptions

interface TTSOptions {
    apiKey?: string;
    apiVersion: string;
    baseUrl: string;
    chunkTimeout: number;
    emotion?: string[];
    encoding: "pcm_s16le";
    language: string;
    model: string;
    pronunciationDictId?: string;
    sampleRate: number;
    speed?: number | TTSVoiceSpeed;
    voice: string | number[];
    volume?: number;
    wordTimestamps?: boolean;
}

Properties

apiKey? apiVersion baseUrl chunkTimeout emotion? encoding language model pronunciationDictId? sampleRate speed? voice volume? wordTimestamps?

Properties

Optional apiKey

apiKey?: string

apiVersion

apiVersion: string

baseUrl

baseUrl: string

chunkTimeout

chunkTimeout: number

The timeout for the next chunk to be received from the Cartesia API.

Optional emotion

emotion?: string[]

encoding

encoding: "pcm_s16le"

language

language: string

model

model: string

Optional pronunciationDictId

pronunciationDictId?: string

sampleRate

sampleRate: number

Optional speed

speed?: number | TTSVoiceSpeed

voice

voice: string | number[]

Optional volume

volume?: number

Volume of the speech. For sonic-3, the value is valid between 0.5 and 2.0.

See

https://docs.cartesia.ai/api-reference/tts/bytes#body-generation-config-volume

Optional wordTimestamps

wordTimestamps?: boolean

Whether to add word timestamps to the output. When enabled, the TTS will return timing information for each word in the transcript.

Default Value

true

Settings

Member Visibility

Theme

On This Page

apiKeyapiVersionbaseUrlchunkTimeoutemotionencodinglanguagemodelpronunciationDictIdsampleRatespeedvoicevolumewordTimestamps