Add MS Edge TTS

public/scripts/extensions/tts/edge.js

@@ -0,0 +1,124 @@
+import { getRequestHeaders } from "../../../script.js"
+import { doExtrasFetch, getApiUrl, modules } from "../../extensions.js"
+import { getPreviewString } from "./index.js"
+
+export { EdgeTtsProvider }
+
+class EdgeTtsProvider {
+    //########//
+    // Config //
+    //########//
+
+    settings
+    voices = []
+    separator = ' .. '
+
+    defaultSettings = {
+        voiceMap: {}
+    }
+
+    get settingsHtml() {
+        let html = `Microsoft Edge TTS Provider<br>`
+        return html
+    }
+
+    onSettingsChange() {
+    }
+
+    loadSettings(settings) {
+        // Pupulate Provider UI given input settings
+        if (Object.keys(settings).length == 0) {
+            console.info("Using default TTS Provider settings")
+        }
+
+        // Only accept keys defined in defaultSettings
+        this.settings = this.defaultSettings
+
+        for (const key in settings){
+            if (key in this.settings){
+                this.settings[key] = settings[key]
+            } else {
+                throw `Invalid setting passed to TTS Provider: ${key}`
+            }
+        }
+
+        console.info("Settings loaded")
+    }
+
+
+    async onApplyClick() {
+        return
+    }
+
+    //#################//
+    //  TTS Interfaces //
+    //#################//
+
+    async getVoice(voiceName) {
+        if (this.voices.length == 0) {
+            this.voices = await this.fetchTtsVoiceIds()
+        }
+        const match = this.voices.filter(
+            voice => voice.name == voiceName
+        )[0]
+        if (!match) {
+            throw `TTS Voice name ${voiceName} not found`
+        }
+        return match
+    }
+
+    async generateTts(text, voiceId){
+        const response = await this.fetchTtsGeneration(text, voiceId)
+        return response
+    }
+
+    //###########//
+    // API CALLS //
+    //###########//
+    async fetchTtsVoiceIds() {
+        const response = await doExtrasFetch(`/edge_voices`)
+        if (!response.ok) {
+            throw new Error(`HTTP ${response.status}: ${await response.json()}`)
+        }
+        let responseJson = await response.json()
+        responseJson = responseJson
+            .sort((a, b) => a.Locale.localeCompare(b.Locale) || a.ShortName.localeCompare(b.ShortName))
+            .map(x => ({ name: x.ShortName, voice_id: x.ShortName, preview_url: false, lang: x.Locale }));
+        return responseJson
+    }
+
+
+    async previewTtsVoice(id) {
+        const voice = await this.getVoice(id);
+        const text = getPreviewString(voice.lang);
+        const response = await this.fetchTtsGeneration(text, id)
+        if (!response.ok) {
+            throw new Error(`HTTP ${response.status}: ${await response.json()}`)
+        }
+
+        const audio = await response.blob();
+        const url = URL.createObjectURL(audio);
+        const audioElement = document.createElement("audio");
+        audioElement.src = url;
+        audioElement.play();
+    }
+
+    async fetchTtsGeneration(inputText, voiceId) {
+        console.info(`Generating new TTS for voice_id ${voiceId}`)
+        const response = await doExtrasFetch(
+            `/edge_speech`,
+            {
+                method: 'POST',
+                headers: getRequestHeaders(),
+                body: JSON.stringify({
+                    "text": inputText,
+                    "voice": voiceId
+                })
+            }
+        )
+        if (!response.ok) {
+            throw new Error(`HTTP ${response.status}: ${await response.json()}`)
+        }
+        return response
+    }
+}

public/scripts/extensions/tts/index.js

@@ -1,6 +1,7 @@
 import { callPopup, cancelTtsPlay, eventSource, event_types, isMultigenEnabled, is_send_press, saveSettingsDebounced } from '../../../script.js'
 import { ModuleWorkerWrapper, extension_settings, getContext } from '../../extensions.js'
 import { getStringHash } from '../../utils.js'
+import { EdgeTtsProvider } from './edge.js'
 import { ElevenLabsTtsProvider } from './elevenlabs.js'
 import { SileroTtsProvider } from './silerotts.js'
 import { SystemTtsProvider } from './system.js'
@@ -15,11 +16,52 @@ let lastGroupId = null
 let lastChatId = null
 let lastMessageHash = null
 
+export function getPreviewString(lang) {
+    const previewStrings = {
+        'en-US': 'The quick brown fox jumps over the lazy dog',
+        'en-GB': 'Sphinx of black quartz, judge my vow',
+        'fr-FR': 'Portez ce vieux whisky au juge blond qui fume',
+        'de-DE': 'Victor jagt zwölf Boxkämpfer quer über den großen Sylter Deich',
+        'it-IT': "Pranzo d'acqua fa volti sghembi",
+        'es-ES': 'Quiere la boca exhausta vid, kiwi, piña y fugaz jamón',
+        'es-MX': 'Fabio me exige, sin tapujos, que añada cerveza al whisky',
+        'ru-RU': 'В чащах юга жил бы цитрус? Да, но фальшивый экземпляр!',
+        'pt-BR': 'Vejo xá gritando que fez show sem playback.',
+        'pt-PR': 'Todo pajé vulgar faz boquinha sexy com kiwi.',
+        'uk-UA': "Фабрикуймо гідність, лящім їжею, ґав хапаймо, з'єднавці чаш!",
+        'pl-PL': 'Pchnąć w tę łódź jeża lub ośm skrzyń fig',
+        'cs-CZ': 'Příliš žluťoučký kůň úpěl ďábelské ódy',
+        'sk-SK': 'Vyhŕňme si rukávy a vyprážajme čínske ryžové cestoviny',
+        'hu-HU': 'Árvíztűrő tükörfúrógép',
+        'tr-TR': 'Pijamalı hasta yağız şoföre çabucak güvendi',
+        'nl-NL': 'De waard heeft een kalfje en een pinkje opgegeten',
+        'sv-SE': 'Yxskaftbud, ge vårbygd, zinkqvarn',
+        'da-DK': 'Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen Walther spillede på xylofon',
+        'ja-JP': 'いろはにほへと　ちりぬるを　わかよたれそ　つねならむ　うゐのおくやま　けふこえて　あさきゆめみし　ゑひもせす',
+        'ko-KR': '가나다라마바사아자차카타파하',
+        'zh-CN': '我能吞下玻璃而不伤身体',
+        'ro-RO': 'Muzicologă în bej vând whisky și tequila, preț fix',
+        'bg-BG': 'Щъркелите се разпръснаха по цялото небе',
+        'el-GR': 'Ταχίστη αλώπηξ βαφής ψημένη γη, δρασκελίζει υπέρ νωθρού κυνός',
+        'fi-FI': 'Voi veljet, miksi juuri teille myin nämä vehkeet?',
+        'he-IL': 'הקצינים צעקו: "כל הכבוד לצבא הצבאות!"',
+        'id-ID': 'Jangkrik itu memang enak, apalagi kalau digoreng',
+        'ms-MY': 'Muzik penyanyi wanita itu menggambarkan kehidupan yang penuh dengan duka nestapa',
+        'th-TH': 'เป็นไงบ้างครับ ผมชอบกินข้าวผัดกระเพราหมูกรอบ',
+        'vi-VN': 'Cô bé quàng khăn đỏ đang ngồi trên bãi cỏ xanh',
+        'ar-SA': 'أَبْجَدِيَّة عَرَبِيَّة',
+        'hi-IN': 'श्वेता ने श्वेता के श्वेते हाथों में श्वेता का श्वेता चावल पकड़ा',
+    }
+    const fallbackPreview = 'Neque porro quisquam est qui dolorem ipsum quia dolor sit amet'
+
+    return  previewStrings[lang] ?? fallbackPreview;
+}
 
 let ttsProviders = {
     ElevenLabs: ElevenLabsTtsProvider,
     Silero: SileroTtsProvider,
     System: SystemTtsProvider,
+    Edge: EdgeTtsProvider,
 }
 let ttsProvider
 let ttsProviderName

public/scripts/extensions/tts/system.js

@@ -1,3 +1,5 @@
+import { getPreviewString } from "./index.js";
+
 export { SystemTtsProvider }
 
 /**
@@ -74,20 +76,6 @@ class SystemTtsProvider {
     // Config //
     //########//
 
-    previewStrings = {
-        'en-US': 'The quick brown fox jumps over the lazy dog',
-        'en-GB': 'Sphinx of black quartz, judge my vow',
-        'fr-FR': 'Portez ce vieux whisky au juge blond qui fume',
-        'de-DE': 'Victor jagt zwölf Boxkämpfer quer über den großen Sylter Deich',
-        'it-IT': "Pranzo d'acqua fa volti sghembi",
-        'es-ES': 'Quiere la boca exhausta vid, kiwi, piña y fugaz jamón',
-        'es-MX': 'Fabio me exige, sin tapujos, que añada cerveza al whisky',
-        'ru-RU': 'В чащах юга жил бы цитрус? Да, но фальшивый экземпляр!',
-        'pt-BR': 'Vejo xá gritando que fez show sem playback.',
-        'pt-PR': 'Todo pajé vulgar faz boquinha sexy com kiwi.',
-        'uk-UA': "Фабрикуймо гідність, лящім їжею, ґав хапаймо, з'єднавці чаш!",
-    }
-    fallbackPreview = 'Neque porro quisquam est qui dolorem ipsum quia dolor sit amet'
     settings
     voices = []
     separator = ' ... '
@@ -172,7 +160,7 @@ class SystemTtsProvider {
         }
 
         speechSynthesis.cancel();
-        const text = this.previewStrings[voice.lang] ?? this.fallbackPreview;
+        const text = getPreviewString(voice.lang);
         const utterance = new SpeechSynthesisUtterance(text);
         utterance.voice = voice;
         utterance.rate = 1;