Interface TTSv2Options

Configuration options for TTSv2 (Deepgram Flux TTS, the /v2/speak endpoint).

interface TTSv2Options {
    apiKey?: string;
    baseUrl: string;
    encoding: "linear16";
    mipOptOut: boolean;
    model: string;
    sampleRate: number;
    wordTokenizer: tokenize.WordTokenizer;
}

Properties

apiKey? baseUrl encoding mipOptOut model sampleRate wordTokenizer

Properties

Optional apiKey

apiKey?: string

Deepgram API key. Falls back to $DEEPGRAM_API_KEY.

baseUrl

baseUrl: string

Base URL for the Deepgram Flux TTS API.

encoding

encoding: "linear16"

Audio encoding to use. Only linear16 is supported: the LiveKit pipeline plays raw PCM and this plugin does not decode compressed audio.

mipOptOut

mipOptOut: boolean

Opt out of the Deepgram Model Improvement Program. Defaults to false (requests may be used to improve models).

See

https://dpgr.am/deepgram-mip

model

model: string

Flux TTS model to use. Model names follow the flux-{voice}-{language} format.

See

https://developers.deepgram.com/docs/flux-tts/overview for available voices.

sampleRate

sampleRate: number

Sample rate of audio in Hz.

wordTokenizer

wordTokenizer: tokenize.WordTokenizer

Tokenizer used to split incoming text into the words sent to Flux.

Settings

Member Visibility

Theme

On This Page

apiKeybaseUrlencodingmipOptOutmodelsampleRatewordTokenizer