Interface MJRoomSpeechSynthesizerOptions

interface MJRoomSpeechSynthesizerOptions {
    ModelID?: string;
    OutputFormat?: string;
    PromptID?: string;
    Voice: string;
}

Properties

ModelID?: string

Pins the TTS model by ID. Recommended whenever the voice matters, since voices are vendor-specific.

OutputFormat?: string

The vendor's output format string (e.g. mp3_44100_128). Default: the vendor's default (MP3 or WAV decode either way).

PromptID?: string

The carrier MJ: AI Prompts row whose bindings choose the model. Default: the runner's Default Text To Speech.

Voice: string

The provider-native voice id or name (required: voices belong to a vendor).