🚀 Auto-deploy: Camila atualizado em 26/05/2026 13:59:50

2026-05-26 13:59:50 +00:00
parent ace6c53448
commit 71e633ce71
316 changed files with 59354 additions and 86 deletions
@@ -0,0 +1,141 @@
+import { OUTPUT_FORMAT } from "./Output";
+import { Readable } from "stream";
+import { Agent } from "http";
+import { ProsodyOptions } from "./Prosody";
+export type Voice = {
+    Name: string;
+    ShortName: string;
+    Gender: string;
+    Locale: string;
+    SuggestedCodec: string;
+    FriendlyName: string;
+    Status: string;
+};
+export declare class MetadataOptions {
+    /**
+     * (optional) any voice locale that is supported by the voice. See the list of all voices for compatibility. If not provided, the locale will be inferred from the `voiceName`.
+     * Changing the voiceName will reset the voiceLocale.
+     */
+    voiceLocale?: string;
+    /**
+     * (optional) whether to enable sentence boundary metadata. Default is `false`
+     */
+    sentenceBoundaryEnabled?: boolean;
+    /**
+     * (optional) whether to enable word boundary metadata. Default is `false`
+     */
+    wordBoundaryEnabled?: boolean;
+}
+/**
+ * MsEdgeTTS constructor options
+ */
+type Options = {
+    /**
+     * (optional, **NOT SUPPORTED IN BROWSER**) Use a custom http.Agent implementation like [https-proxy-agent](https://github.com/TooTallNate/proxy-agents) or [socks-proxy-agent](https://github.com/TooTallNate/proxy-agents/tree/main/packages/socks-proxy-agent).
+     * */
+    agent?: Agent;
+    /** whether to enable the built-in logger. This logs connections inits, disconnects, and incoming data to the console */
+    enableLogger?: boolean;
+};
+export declare class MsEdgeTTS {
+    private static TRUSTED_CLIENT_TOKEN;
+    private static VOICES_URL;
+    private static WSS_URL;
+    private static JSON_XML_DELIM;
+    private static AUDIO_DELIM;
+    private static VOICE_LANG_REGEX;
+    private readonly _enableLogger;
+    private readonly _isBrowser;
+    private _ws;
+    private _voice;
+    private _outputFormat;
+    private _metadataOptions;
+    private _streams;
+    private _startTime;
+    private readonly _agent;
+    private _log;
+    /**
+     * Create a new `MsEdgeTTS` instance.
+     *
+     * @param options (optional) {@link Options}
+     */
+    constructor(options?: Options);
+    private static getSynthUrl;
+    private _initClient;
+    private static generateUUID;
+    private static generateSecMsGec;
+    private _send;
+    private _pushAudioData;
+    private _pushMetadata;
+    private _SSMLTemplate;
+    /**
+     * Fetch the list of voices available in Microsoft Edge.
+     * These, however, are not all. The complete list of voices supported by this module [can be found here](https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support) (neural, standard, and preview).
+     */
+    getVoices(): Promise<Voice[]>;
+    /**
+     * Sets the required information for the speech to be synthesised and inits a new WebSocket connection.
+     * Must be called at least once before text can be synthesised.
+     * Saved in this instance. Can be called at any time times to update the metadata.
+     * Merges specified values into previously provided values.
+     *
+     * @param voiceName a string with any `ShortName`. A list of all available neural voices can be found [here](https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support#neural-voices). However, it is not limited to neural voices: standard voices can also be used. A list of standard voices can be found [here](https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/language-support#standard-voices). Changing the voiceName will reset the voiceLocale.
+     * @param outputFormat any {@link OUTPUT_FORMAT}
+     * @param metadataOptions (optional) {@link MetadataOptions}
+     */
+    setMetadata(voiceName: string, outputFormat: OUTPUT_FORMAT, metadataOptions?: MetadataOptions): Promise<void>;
+    private _metadataCheck;
+    /**
+     * Close the WebSocket connection.
+     */
+    close(): void;
+    /**
+     * Writes raw audio synthesised from text to a file. Uses a basic {@link _SSMLTemplate SML template}.
+     *
+     * @param dirPath a valid output directory path
+     * @param input the input to synthesise
+     * @param options (optional) {@link ProsodyOptions}
+     @returns {Promise<{audioFilePath: string, metadataFilePath: string | null}>} - a `Promise` with the full filepaths
+     */
+    toFile(dirPath: string, input: string, options?: ProsodyOptions): Promise<{
+        audioFilePath: string;
+        metadataFilePath: string | null;
+    }>;
+    /**
+     * Writes raw audio synthesised from text in real-time to a {@link Readable}. Uses a basic {@link _SSMLTemplate SML template}.
+     *
+     * @param input the text to synthesise. Can include SSML elements.
+     * @param options (optional) {@link ProsodyOptions}
+     @returns {Promise<{audioStream: Readable, metadataStream: Readable | null}>} - a `Promise` with the streams
+     */
+    toStream(input: string, options?: ProsodyOptions): {
+        audioStream: Readable;
+        metadataStream: Readable | null;
+    };
+    /**
+     * Writes raw audio synthesised from text to a file. Has no SSML template. Basic SSML should be provided in the request.
+     *
+     * @param dirPath a valid output directory path.
+     * @param requestSSML the SSML to send. SSML elements required in order to work.
+     * @returns {Promise<{audioFilePath: string, metadataFilePath: string | null}>} - a `Promise` with the full filepaths
+     */
+    rawToFile(dirPath: string, requestSSML: string): Promise<{
+        audioFilePath: string;
+        metadataFilePath: string | null;
+    }>;
+    /**
+     * Writes raw audio synthesised from a request in real-time to a {@link Readable}. Has no SSML template. Basic SSML should be provided in the request.
+     *
+     * @param requestSSML the SSML to send. SSML elements required in order to work.
+     @returns {Promise<{audioStream: Readable, metadataStream: Readable | null}>} - a `Promise` with the streams
+     */
+    rawToStream(requestSSML: string): {
+        audioStream: Readable;
+        metadataStream: Readable | null;
+    };
+    private _hasMetadataBoundaries;
+    private _rawSSMLRequestToFile;
+    private static randomHex;
+    private _rawSSMLRequest;
+}
+export {};