@bestcodes/edge-tts 1.0.1

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 The-Best-Codes
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -0,0 +1,115 @@
+# @bestcodes/edge-tts
+
+[![npm version](https://badge.fury.io/js/%40bestcodes%2Fedge-tts.svg)](https://badge.fury.io/js/%40bestcodes%2Fedge-tts)
+
+## This is a fork.
+
+The original version, here:
+https://github.com/Migushthe2nd/MsEdgeTTS
+Was undermaintained and had dependency issues, so I forked the repo and fixed them.
+
+An simple Azure Speech Service module that uses the Microsoft Edge Read Aloud API.
+
+Only supports `speak`, `voice`, and `prosody` element types. The following is the default SSML object:
+
+```xml
+<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts"
+       xml:lang="${this._voiceLang}">
+    <voice name="${voiceName}">
+        <prosody rate="${rate}" pitch="${pitch}" volume="${volume}">
+            ${input}
+        </prosody>
+    </voice>
+</speak>
+```
+
+Documentation on the SSML
+format [can be found here](https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-synthesis-markup)
+. All supported audio formats [can be found here](./src/OUTPUT_FORMAT.ts).
+
+## Example usage
+
+Make sure to **escape/sanitize** your user's input!
+Use a library like [xml-escape](https://www.npmjs.com/package/xml-escape).
+
+### Write to stream
+
+```js
+import { MsEdgeTTS, OUTPUT_FORMAT } from "msedge-tts";
+
+const tts = new MsEdgeTTS();
+await tts.setMetadata(
+  "en-IE-ConnorNeural",
+  OUTPUT_FORMAT.WEBM_24KHZ_16BIT_MONO_OPUS
+);
+const readable = tts.toStream("Hi, how are you?");
+
+readable.on("data", (data) => {
+  console.log("DATA RECEIVED", data);
+  // raw audio file data
+});
+
+readable.on("close", () => {
+  console.log("STREAM CLOSED");
+});
+```
+
+### Write to file
+
+```js
+import { MsEdgeTTS, OUTPUT_FORMAT } from "msedge-tts";
+
+(async () => {
+  const tts = new MsEdgeTTS();
+  await tts.setMetadata(
+    "en-US-AriaNeural",
+    OUTPUT_FORMAT.WEBM_24KHZ_16BIT_MONO_OPUS
+  );
+  const filePath = await tts.toFile("./example_audio.webm", "Hi, how are you?");
+})();
+```
+
+### Change voice rate, pitch and volume
+
+```js
+import { MsEdgeTTS, OUTPUT_FORMAT } from "msedge-tts";
+
+(async () => {
+  const tts = new MsEdgeTTS();
+  await tts.setMetadata(
+    "en-US-AriaNeural",
+    OUTPUT_FORMAT.WEBM_24KHZ_16BIT_MONO_OPUS
+  );
+  const filePath = await tts.toFile(
+    "./example_audio.webm",
+    "Hi, how are you?",
+    { rate: 0.5, pitch: "+200Hz" }
+  );
+})();
+```
+
+### Use an alternative HTTP Agent
+
+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).
+
+```js
+import { SocksProxyAgent } from "socks-proxy-agent";
+
+(async () => {
+  const agent = new SocksProxyAgent(
+    "socks://your-name%40gmail.com:abcdef12345124@br41.nordvpn.com"
+  );
+  const tts = new MsEdgeTTS(agent);
+  await tts.setMetadata(
+    "en-US-AriaNeural",
+    OUTPUT_FORMAT.WEBM_24KHZ_16BIT_MONO_OPUS
+  );
+  const filePath = await tts.toFile("./example_audio.webm", "Hi, how are you?");
+})();
+```
+
+## API
+
+For the full documentation check out the [API Documentation](https://migushthe2nd.github.io/MsEdgeTTS).
+
+This library only supports promises.

package/dist/MsEdgeTTS.js

@@ -0,0 +1 @@
+"use strict";var __assign=this&&this.__assign||function(){return __assign=Object.assign||function(t){for(var e,n=1,o=arguments.length;n<o;n++)for(var a in e=arguments[n])Object.prototype.hasOwnProperty.call(e,a)&&(t[a]=e[a]);return t},__assign.apply(this,arguments)},__createBinding=this&&this.__createBinding||(Object.create?function(t,e,n,o){void 0===o&&(o=n);var a=Object.getOwnPropertyDescriptor(e,n);a&&!("get"in a?!e.__esModule:a.writable||a.configurable)||(a={enumerable:!0,get:function(){return e[n]}}),Object.defineProperty(t,o,a)}:function(t,e,n,o){void 0===o&&(o=n),t[o]=e[n]}),__setModuleDefault=this&&this.__setModuleDefault||(Object.create?function(t,e){Object.defineProperty(t,"default",{enumerable:!0,value:e})}:function(t,e){t.default=e}),__importStar=this&&this.__importStar||function(t){if(t&&t.__esModule)return t;var e={};if(null!=t)for(var n in t)"default"!==n&&Object.prototype.hasOwnProperty.call(t,n)&&__createBinding(e,t,n);return __setModuleDefault(e,t),e},__awaiter=this&&this.__awaiter||function(t,e,n,o){return new(n||(n=Promise))((function(a,r){function s(t){try{c(o.next(t))}catch(t){r(t)}}function i(t){try{c(o.throw(t))}catch(t){r(t)}}function c(t){var e;t.done?a(t.value):(e=t.value,e instanceof n?e:new n((function(t){t(e)}))).then(s,i)}c((o=o.apply(t,e||[])).next())}))},__generator=this&&this.__generator||function(t,e){var n,o,a,r,s={label:0,sent:function(){if(1&a[0])throw a[1];return a[1]},trys:[],ops:[]};return r={next:i(0),throw:i(1),return:i(2)},"function"==typeof Symbol&&(r[Symbol.iterator]=function(){return this}),r;function i(i){return function(c){return function(i){if(n)throw new TypeError("Generator is already executing.");for(;r&&(r=0,i[0]&&(s=0)),s;)try{if(n=1,o&&(a=2&i[0]?o.return:i[0]?o.throw||((a=o.return)&&a.call(o),0):o.next)&&!(a=a.call(o,i[1])).done)return a;switch(o=0,a&&(i=[2&i[0],a.value]),i[0]){case 0:case 1:a=i;break;case 4:return s.label++,{value:i[1],done:!1};case 5:s.label++,o=i[1],i=[0];continue;case 7:i=s.ops.pop(),s.trys.pop();continue;default:if(!(a=s.trys,(a=a.length>0&&a[a.length-1])||6!==i[0]&&2!==i[0])){s=0;continue}if(3===i[0]&&(!a||i[1]>a[0]&&i[1]<a[3])){s.label=i[1];break}if(6===i[0]&&s.label<a[1]){s.label=a[1],a=i;break}if(a&&s.label<a[2]){s.label=a[2],s.ops.push(i);break}a[2]&&s.ops.pop(),s.trys.pop();continue}i=e.call(t,s)}catch(t){i=[6,t],o=0}finally{n=a=0}if(5&i[0])throw i[1];return{value:i[0]?i[1]:void 0,done:!0}}([i,c])}}},__importDefault=this&&this.__importDefault||function(t){return t&&t.__esModule?t:{default:t}};Object.defineProperty(exports,"__esModule",{value:!0}),exports.MsEdgeTTS=exports.MetadataOptions=exports.ProsodyOptions=void 0;var axios_1=__importDefault(require("axios")),isomorphic_ws_1=__importDefault(require("isomorphic-ws")),buffer_1=require("buffer/"),randombytes_1=__importDefault(require("randombytes")),OUTPUT_FORMAT_1=require("./OUTPUT_FORMAT"),stream_1=require("stream"),fs=__importStar(require("fs")),ProsodyOptions=function(){this.pitch="+0Hz",this.rate=1,this.volume=100};exports.ProsodyOptions=ProsodyOptions;var messageTypes,MetadataOptions=function(){this.sentenceBoundaryEnabled=!1,this.wordBoundaryEnabled=!1};exports.MetadataOptions=MetadataOptions,function(t){t.TURN_START="turn.start",t.TURN_END="turn.end",t.RESPONSE="response",t.SPEECH_CONFIG="speech.config",t.AUDIO_METADATA="audio.metadata",t.AUDIO="audio",t.SSML="ssml"}(messageTypes||(messageTypes={}));var MsEdgeTTS=function(){function t(t,e){void 0===e&&(e=!1),this._metadataOptions=new MetadataOptions,this._streams={},this._startTime=0,this._agent=t,this._enableLogger=e,this._isBrowser="undefined"!=typeof window&&void 0!==window.document}return t.prototype._log=function(){for(var t=[],e=0;e<arguments.length;e++)t[e]=arguments[e];this._enableLogger&&console.log.apply(console,t)},t.prototype._send=function(t){return __awaiter(this,void 0,void 0,(function(){var e,n=this;return __generator(this,(function(o){switch(o.label){case 0:e=1,o.label=1;case 1:return e<=3&&this._ws.readyState!==this._ws.OPEN?(1==e&&(this._startTime=Date.now()),this._log("connecting: ",e),[4,this._initClient()]):[3,4];case 2:o.sent(),o.label=3;case 3:return e++,[3,1];case 4:return this._ws.send(t,(function(){n._log("<-",t)})),[2]}}))}))},t.prototype._initClient=function(){var e=this;return this._ws=this._isBrowser?new isomorphic_ws_1.default(t.SYNTH_URL):new isomorphic_ws_1.default(t.SYNTH_URL,{agent:this._agent}),this._ws.binaryType="arraybuffer",new Promise((function(n,o){e._ws.onopen=function(){e._log("Connected in",(Date.now()-e._startTime)/1e3,"seconds"),e._send("Content-Type:application/json; charset=utf-8\r\nPath:".concat(messageTypes.SPEECH_CONFIG).concat(t.JSON_XML_DELIM,'\n                    {\n                        "context": {\n                            "synthesis": {\n                                "audio": {\n                                    "metadataoptions": {\n                                        "sentenceBoundaryEnabled": "').concat(e._metadataOptions.sentenceBoundaryEnabled,'",\n                                        "wordBoundaryEnabled": "').concat(e._metadataOptions.wordBoundaryEnabled,'"\n                                    },\n                                    "outputFormat": "').concat(e._outputFormat,'" \n                                }\n                            }\n                        }\n                    }\n                ')).then(n)},e._ws.onmessage=function(n){var o,a=buffer_1.Buffer.from(n.data),r=a.toString(),s=(null===(o=/X-RequestId:(.*?)\r\n/gm.exec(r))||void 0===o?void 0:o[1])||"";if(r.includes("Path:".concat(messageTypes.TURN_START)))e._log("->",r);else if(r.includes("Path:".concat(messageTypes.TURN_END)))e._log("->",r),e._streams[s].audio.push(null);else if(r.includes("Path:".concat(messageTypes.RESPONSE)))e._log("->",r);else if(r.includes("Path:".concat(messageTypes.AUDIO_METADATA))){var i=a.indexOf(t.JSON_XML_DELIM)+t.JSON_XML_DELIM.length,c=a.subarray(i);e._log("->",r),e._pushMetadata(c,s)}else if(r.includes("Path:".concat(messageTypes.AUDIO))&&n.data instanceof ArrayBuffer){i=a.indexOf(t.AUDIO_DELIM)+t.AUDIO_DELIM.length;var u=a.subarray(0,i).toString();c=a.subarray(i);e._log("->",u),e._pushAudioData(c,s)}else e._log("->","UNKNOWN MESSAGE",r)},e._ws.onclose=function(){for(var t in e._log("disconnected after:",(Date.now()-e._startTime)/1e3,"seconds"),e._streams)e._streams[t].audio.push(null)},e._ws.onerror=function(t){o("Connect Error: "+JSON.stringify(t,null,2))}}))},t.prototype._pushAudioData=function(t,e){this._streams[e].audio.push(t)},t.prototype._pushMetadata=function(t,e){this._streams[e].metadata.push(t)},t.prototype._SSMLTemplate=function(t,e){return void 0===e&&(e={}),e=__assign(__assign({},new ProsodyOptions),e),'<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="'.concat(this._metadataOptions.voiceLocale,'">\n                <voice name="').concat(this._voice,'">\n                    <prosody pitch="').concat(e.pitch,'" rate="').concat(e.rate,'" volume="').concat(e.volume,'">\n                        ').concat(t,"\n                    </prosody> \n                </voice>\n            </speak>")},t.prototype.getVoices=function(){return new Promise((function(e,n){axios_1.default.get(t.VOICES_URL).then((function(t){return e(t.data)})).catch(n)}))},t.prototype.setMetadata=function(e,n,o){return __awaiter(this,void 0,void 0,(function(){var a,r,s,i;return __generator(this,(function(c){switch(c.label){case 0:if(a=this._voice,r=this._outputFormat,s=JSON.stringify(this._metadataOptions),this._voice=e,!this._metadataOptions.voiceLocale||o&&!o.voiceLocale&&a!==this._voice){if(!(i=t.VOICE_LANG_REGEX.exec(this._voice)))throw new Error("Could not infer voiceLocale from voiceName, and no voiceLocale was specified!");this._metadataOptions.voiceLocale=i[0]}return this._outputFormat=n,Object.assign(this._metadataOptions,o),a!==this._voice||r!==this._outputFormat||s!==JSON.stringify(this._metadataOptions)||this._ws.readyState!==this._ws.OPEN?(this._startTime=Date.now(),[4,this._initClient()]):[2];case 1:return c.sent(),[2]}}))}))},t.prototype._metadataCheck=function(){if(!this._ws)throw new Error("Speech synthesis not configured yet. Run setMetadata before calling toStream or toFile.")},t.prototype.close=function(){this._ws.close()},t.prototype.toFile=function(t,e,n){return this._rawSSMLRequestToFile(t,this._SSMLTemplate(e,n))},t.prototype.toStream=function(t,e){return this._rawSSMLRequest(this._SSMLTemplate(t,e)).audioStream},t.prototype.rawToFile=function(t,e){return this._rawSSMLRequestToFile(t,e)},t.prototype.rawToStream=function(t){return this._rawSSMLRequest(t).audioStream},t.prototype._rawSSMLRequestToFile=function(t,e){return __awaiter(this,void 0,void 0,(function(){var n,o,a,r,s,i,c,u=this;return __generator(this,(function(_){switch(_.label){case 0:n=this._rawSSMLRequest(e),o=n.audioStream,a=n.metadataStream,n.requestId,_.label=1;case 1:return _.trys.push([1,3,,4]),[4,Promise.all([new Promise((function(e,n){var r=o.pipe(fs.createWriteStream(t+"/example_audio.webm"));r.once("close",(function(){return __awaiter(u,void 0,void 0,(function(){return __generator(this,(function(o){return r.bytesWritten>0?e(t+"/example_audio.webm"):n("No audio data received"),[2]}))}))})),a.once("error",n)})),new Promise((function(e,n){var o=[];a.on("data",(function(t){var e=JSON.parse(t.toString());o.push.apply(o,e.Metadata)})),a.on("close",(function(){var n=t+"/example_metadata.json";fs.writeFileSync(n,JSON.stringify(o,null,2)),e(n)})),a.once("error",n)}))])];case 2:return r=_.sent(),s=r[0],i=r[1],[2,{audioFilePath:s,metadataFilePath:i}];case 3:throw c=_.sent(),o.destroy(),a.destroy(),c;case 4:return[2]}}))}))},t.prototype._rawSSMLRequest=function(e){this._metadataCheck();var n=(0,randombytes_1.default)(16).toString("hex"),o="X-RequestId:".concat(n,"\r\nContent-Type:application/ssml+xml\r\nPath:").concat(messageTypes.SSML).concat(t.JSON_XML_DELIM)+e.trim(),a=this,r=new stream_1.Readable({read:function(){},destroy:function(t,e){delete a._streams[n],e(t)}}),s=new stream_1.Readable({read:function(){}});return r.on("error",(function(t){r.destroy(),s.destroy()})),r.once("close",(function(){r.destroy(),s.destroy()})),this._streams[n]={audio:r,metadata:s},this._send(o).then(),{audioStream:r,metadataStream:s,requestId:n}},t.OUTPUT_FORMAT=OUTPUT_FORMAT_1.OUTPUT_FORMAT,t.TRUSTED_CLIENT_TOKEN="6A5AA1D4EAFF4E9FB37E23D68491D6F4",t.VOICES_URL="https://speech.platform.bing.com/consumer/speech/synthesize/readaloud/voices/list?trustedclienttoken=".concat(t.TRUSTED_CLIENT_TOKEN),t.SYNTH_URL="wss://speech.platform.bing.com/consumer/speech/synthesize/readaloud/edge/v1?TrustedClientToken=".concat(t.TRUSTED_CLIENT_TOKEN),t.JSON_XML_DELIM="\r\n\r\n",t.AUDIO_DELIM="Path:audio\r\n",t.VOICE_LANG_REGEX=/\w{2}-\w{2}/,t}();exports.MsEdgeTTS=MsEdgeTTS;

package/dist/OUTPUT_FORMAT.js

@@ -0,0 +1 @@
+"use strict";var OUTPUT_FORMAT;Object.defineProperty(exports,"__esModule",{value:!0}),exports.OUTPUT_FORMAT=void 0,function(O){O.AUDIO_24KHZ_48KBITRATE_MONO_MP3="audio-24khz-48kbitrate-mono-mp3",O.AUDIO_24KHZ_96KBITRATE_MONO_MP3="audio-24khz-96kbitrate-mono-mp3",O.WEBM_24KHZ_16BIT_MONO_OPUS="webm-24khz-16bit-mono-opus"}(OUTPUT_FORMAT||(exports.OUTPUT_FORMAT=OUTPUT_FORMAT={}));

package/dist/PITCH.js

@@ -0,0 +1 @@
+"use strict";var PITCH;Object.defineProperty(exports,"__esModule",{value:!0}),exports.PITCH=void 0,function(e){e.X_LOW="x-low",e.LOW="low",e.MEDIUM="medium",e.HIGH="high",e.X_HIGH="x-high",e.DEFAULT="default"}(PITCH||(exports.PITCH=PITCH={}));

package/dist/RATE.js

@@ -0,0 +1 @@
+"use strict";var RATE;Object.defineProperty(exports,"__esModule",{value:!0}),exports.RATE=void 0,function(e){e.X_SLOW="x-slow",e.SLOW="slow",e.MEDIUM="medium",e.FAST="fast",e.X_FAST="x-fast",e.DEFAULT="default"}(RATE||(exports.RATE=RATE={}));

package/dist/VOLUME.js

@@ -0,0 +1 @@
+"use strict";var VOLUME;Object.defineProperty(exports,"__esModule",{value:!0}),exports.VOLUME=void 0,function(e){e.SILENT="silent",e.X_SOFT="x-soft",e.SOFT="soft",e.MEDIUM="medium",e.LOUD="loud",e.X_LOUD="x-LOUD",e.DEFAULT="default"}(VOLUME||(exports.VOLUME=VOLUME={}));

package/dist/index.js

@@ -0,0 +1 @@
+"use strict";Object.defineProperty(exports,"__esModule",{value:!0}),exports.VOLUME=exports.RATE=exports.PITCH=exports.OUTPUT_FORMAT=exports.ProsodyOptions=exports.MsEdgeTTS=void 0;var MsEdgeTTS_1=require("./MsEdgeTTS");Object.defineProperty(exports,"MsEdgeTTS",{enumerable:!0,get:function(){return MsEdgeTTS_1.MsEdgeTTS}}),Object.defineProperty(exports,"ProsodyOptions",{enumerable:!0,get:function(){return MsEdgeTTS_1.ProsodyOptions}});var OUTPUT_FORMAT_1=require("./OUTPUT_FORMAT");Object.defineProperty(exports,"OUTPUT_FORMAT",{enumerable:!0,get:function(){return OUTPUT_FORMAT_1.OUTPUT_FORMAT}});var PITCH_1=require("./PITCH");Object.defineProperty(exports,"PITCH",{enumerable:!0,get:function(){return PITCH_1.PITCH}});var RATE_1=require("./RATE");Object.defineProperty(exports,"RATE",{enumerable:!0,get:function(){return RATE_1.RATE}});var VOLUME_1=require("./VOLUME");Object.defineProperty(exports,"VOLUME",{enumerable:!0,get:function(){return VOLUME_1.VOLUME}});

package/dist/types/MsEdgeTTS.d.ts

@@ -0,0 +1,141 @@
+import { OUTPUT_FORMAT } from "./OUTPUT_FORMAT";
+import { Readable } from "stream";
+import { Agent } from "http";
+import { PITCH } from "./PITCH";
+import { RATE } from "./RATE";
+import { VOLUME } from "./VOLUME";
+export type Voice = {
+    Name: string;
+    ShortName: string;
+    Gender: string;
+    Locale: string;
+    SuggestedCodec: string;
+    FriendlyName: string;
+    Status: string;
+};
+export declare class ProsodyOptions {
+    /**
+     * The pitch to use.
+     * Can be any {@link PITCH}, or a relative frequency in Hz (+50Hz), a relative semitone (+2st), or a relative percentage (+50%).
+     * [SSML documentation](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice#:~:text=Optional-,pitch,-Indicates%20the%20baseline)
+     */
+    pitch?: PITCH | string;
+    /**
+     * The rate to use.
+     * Can be any {@link RATE}, or a relative number (0.5), or string with a relative percentage (+50%).
+     * [SSML documentation](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice#:~:text=Optional-,rate,-Indicates%20the%20speaking)
+     */
+    rate?: RATE | string | number;
+    /**
+     * The volume to use.
+     * Can be any {@link VOLUME}, or an absolute number (0, 100), a string with a relative number (+50), or a relative percentage (+50%).
+     * [SSML documentation](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice#:~:text=Optional-,volume,-Indicates%20the%20volume)
+     */
+    volume?: VOLUME | string | number;
+}
+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;
+}
+export declare class MsEdgeTTS {
+    static OUTPUT_FORMAT: typeof OUTPUT_FORMAT;
+    private static TRUSTED_CLIENT_TOKEN;
+    private static VOICES_URL;
+    private static SYNTH_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 agent (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).
+     * @param enableLogger=false whether to enable the built-in logger. This logs connections inits, disconnects, and incoming data to the console
+     */
+    constructor(agent?: Agent, enableLogger?: boolean);
+    private _send;
+    private _initClient;
+    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.
+     *
+     * @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}>} - a `Promise` with the full filepaths
+       */
+    toFile(dirPath: string, input: string, options?: ProsodyOptions): Promise<{
+        audioFilePath: string;
+        metadataFilePath: string;
+    }>;
+    /**
+     * 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 {Readable} - a `stream.Readable` with the audio data
+     */
+    toStream(input: string, options?: ProsodyOptions): Readable;
+    /**
+     * 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}>} - a `Promise` with the full filepaths
+     */
+    rawToFile(dirPath: string, requestSSML: string): Promise<{
+        audioFilePath: string;
+        metadataFilePath: string;
+    }>;
+    /**
+     * 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 {Readable} - a `stream.Readable` with the audio data
+     */
+    rawToStream(requestSSML: string): Readable;
+    private _rawSSMLRequestToFile;
+    private _rawSSMLRequest;
+}

package/dist/types/OUTPUT_FORMAT.d.ts

@@ -0,0 +1,8 @@
+/**
+ * Only a few of the [possible formats](https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/rest-text-to-speech#audio-outputs) are accepted.
+ */
+export 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"
+}

package/dist/types/PITCH.d.ts

@@ -0,0 +1,11 @@
+/**
+ * https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice#:~:text=Optional-,pitch,-Indicates%20the%20baseline
+ */
+export declare enum PITCH {
+    X_LOW = "x-low",
+    LOW = "low",
+    MEDIUM = "medium",
+    HIGH = "high",
+    X_HIGH = "x-high",
+    DEFAULT = "default"
+}

package/dist/types/RATE.d.ts

@@ -0,0 +1,11 @@
+/**
+ * https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice#:~:text=Optional-,rate,-Indicates%20the%20speaking
+ */
+export declare enum RATE {
+    X_SLOW = "x-slow",
+    SLOW = "slow",
+    MEDIUM = "medium",
+    FAST = "fast",
+    X_FAST = "x-fast",
+    DEFAULT = "default"
+}

package/dist/types/VOLUME.d.ts

@@ -0,0 +1,12 @@
+/**
+ * https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice#:~:text=Optional-,volume,-Indicates%20the%20volume
+ */
+export declare enum VOLUME {
+    SILENT = "silent",
+    X_SOFT = "x-soft",
+    SOFT = "soft",
+    MEDIUM = "medium",
+    LOUD = "loud",
+    X_LOUD = "x-LOUD",
+    DEFAULT = "default"
+}

package/dist/types/index.d.ts

@@ -0,0 +1,5 @@
+export { MsEdgeTTS, Voice, ProsodyOptions } from "./MsEdgeTTS";
+export { OUTPUT_FORMAT } from "./OUTPUT_FORMAT";
+export { PITCH } from "./PITCH";
+export { RATE } from "./RATE";
+export { VOLUME } from "./VOLUME";

package/package.json

@@ -0,0 +1,50 @@
+{
+  "name": "@bestcodes/edge-tts",
+  "version": "1.0.1",
+  "description": "An Azure Speech Service module that uses the Microsoft Edge Read Aloud API.",
+  "author": "The-Best-Codes",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/The-Best-Codes/edge-tts.git"
+  },
+  "bugs": {
+    "url": "https://github.com/The-Best-Codes/edge-tts/issues"
+  },
+  "homepage": "https://github.com/The-Best-Codes/edge-tts#readme",
+  "keywords": [
+    "tts",
+    "text-to-speech",
+    "speech",
+    "text",
+    "voice",
+    "ssml",
+    "azure",
+    "speech-synthesis",
+    "readaloud",
+    "edge",
+    "microsoft"
+  ],
+  "module": "./dist/index",
+  "main": "./dist/index",
+  "scripts": {
+    "minify": "find dist/ -name '*.js' -type f -exec terser {} --compress --mangle --output {} \\;",
+    "build": "tsc --project tsconfig.json --outDir dist && npm run minify",
+    "prepublishOnly": "npm run build",
+    "depclean": "sh depclean.sh",
+    "update": "npm update --save && npm update --save-dev && npx npm-check-updates@latest -u && npm install",
+    "maintain": "npm run depclean && npm run update"
+  },
+  "devDependencies": {
+    "@types/node": "^22.8.1",
+    "@types/randombytes": "^2.0.3",
+    "axios": "^1.7.7",
+    "buffer": "^6.0.3",
+    "isomorphic-ws": "^5.0.0",
+    "randombytes": "^2.1.0",
+    "terser": "^5.36.0"
+  },
+  "files": [
+    "dist/"
+  ]
+}