edge-tts-generator/dist/index.d.mts

Generate text-to-speech narration for free, leveraging the Read Aloud feature in Microsoft Edge

declare enum OUTPUT_FORMAT {
    AUDIO_24KHZ_48KBITRATE_MONO_MP3 = "audio-24khz-48kbitrate-mono-mp3",
    AUDIO_24KHZ_96KBITRATE_MONO_MP3 = "audio-24khz-96kbitrate-mono-mp3",
    WEBM_24KHZ_16BIT_MONO_OPUS = "webm-24khz-16bit-mono-opus"
}
declare enum PITCH {
    X_LOW = "x-low",
    LOW = "low",
    MEDIUM = "medium",
    HIGH = "high",
    X_HIGH = "x-high",
    DEFAULT = "default"
}
declare enum RATE {
    X_SLOW = "x-slow",
    SLOW = "slow",
    MEDIUM = "medium",
    FAST = "fast",
    X_FAST = "x-fast",
    DEFAULT = "default"
}
declare enum VOLUME {
    SILENT = "silent",
    X_SOFT = "x-soft",
    SOFT = "soft",
    MEDIUM = "medium",
    LOUD = "loud",
    X_LOUD = "x-LOUD",
    DEFAULT = "default"
}

type EventType = "data" | "close" | "end" | "error";
declare class EventEmitter {
    private eventListeners;
    constructor();
    on(event: EventType, callback: (...args: any[]) => void): void;
    emit(event: EventType, data: any): void;
}
type Voice = {
    Name: string;
    ShortName: string;
    Gender: string;
    Locale: string;
    SuggestedCodec: string;
    FriendlyName: string;
    Status: string;
};
declare class ProsodyOptions {
    pitch: PITCH | string;
    rate: RATE | string | number;
    volume: VOLUME | string | number;
}
declare class EdgeTTSClient {
    static OUTPUT_FORMAT: typeof OUTPUT_FORMAT;
    private static CLIENT_TOKEN;
    private static VOICES_URL;
    private static SYNTH_URL;
    private static BINARY_DELIM;
    private static VOICE_LANG_REGEX;
    private enableLogging;
    private ws;
    private voice;
    private voiceLocale;
    private outputFormat;
    private requestQueue;
    private connectionStartTime;
    constructor(enableLogging?: boolean);
    private log;
    private sendMessage;
    private initWebSocket;
    private handleMessage;
    private handleClose;
    private cacheAudioData;
    private findDelimiterIndex;
    private getConfigMessage;
    getVoices(): Promise<Voice[]>;
    setMetadata(voiceName: string, outputFormat: OUTPUT_FORMAT, voiceLocale?: string): Promise<void>;
    private inferLocaleFromVoiceName;
    close(): void;
    toStream(text: string, options?: ProsodyOptions): EventEmitter;
    private buildSSML;
    private sendSSMLRequest;
}

type TextToSpeechOptions = {
    voice?: string;
    speed?: number;
    enableLogging?: boolean;
    disableFilter?: boolean;
};
type TextToSpeechProps = {
    text: string;
    outputPath: string;
    fileName: string;
    options?: TextToSpeechOptions;
};
declare function textToSpeechMp3({ text, outputPath, fileName, options, }: TextToSpeechProps): Promise<void>;
type TextToSpeechInput = {
    text: string;
    title: string;
    options?: TextToSpeechOptions;
};
declare function batchTextToSpeechMp3(inputs: TextToSpeechInput[], outputPath: string, globalOptions?: TextToSpeechOptions): Promise<void>;

export { EdgeTTSClient, OUTPUT_FORMAT, PITCH, ProsodyOptions, RATE, type TextToSpeechInput, type TextToSpeechOptions, type TextToSpeechProps, VOLUME, type Voice, batchTextToSpeechMp3, textToSpeechMp3 };