rixty
/
SillyTavern
mirror of https://github.com/SillyTavern/SillyTavern.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

TTS: add slash command to speak

This commit is contained in:
Cohee 2023-11-09 02:57:40 +02:00
parent ca1c0e35b1
commit f2a96427a8
4 changed files with 87 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
public/script.js
View File

@ -6697,6 +6697,7 @@ window["SillyTavern"].getContext = function () {
deactivateSendButtons,
saveReply,
registerSlashCommand: registerSlashCommand,
executeSlashCommands: executeSlashCommands,
registerHelper: registerExtensionHelper,
registedDebugFunction: registerDebugFunction,
renderExtensionTemplate: renderExtensionTemplate,

98
public/scripts/extensions/tts/index.js
View File

@ -1,4 +1,4 @@
import { callPopup, cancelTtsPlay, eventSource, event_types, saveSettingsDebounced } from '../../../script.js'
import { callPopup, cancelTtsPlay, eventSource, event_types, name2, saveSettingsDebounced } from '../../../script.js'
import { ModuleWorkerWrapper, doExtrasFetch, extension_settings, getApiUrl, getContext, modules } from '../../extensions.js'
import { escapeRegex, getStringHash } from '../../utils.js'
import { EdgeTtsProvider } from './edge.js'
@ -8,6 +8,7 @@ import { CoquiTtsProvider } from './coqui.js'
import { SystemTtsProvider } from './system.js'
import { NovelTtsProvider } from './novel.js'
import { power_user } from '../../power-user.js'
import { registerSlashCommand } from '../../slash-commands.js'
export { talkingAnimation };
const UPDATE_INTERVAL = 1000
@ -91,6 +92,36 @@ async function onNarrateOneMessage() {
moduleWorker();
}
async function onNarrateText(args, text) {
if (!text) {
return;
}
audioElement.src = '/sounds/silence.mp3';
// To load all characters in the voice map, set unrestricted to true
await initVoiceMap(true);
const baseName = args?.voice || name2;
const name = (baseName === 'SillyTavern System' ? DEFAULT_VOICE_MARKER : baseName) || DEFAULT_VOICE_MARKER;
const voiceMapEntry = voiceMap[name] === DEFAULT_VOICE_MARKER
? voiceMap[DEFAULT_VOICE_MARKER]
: voiceMap[name];
if (!voiceMapEntry || voiceMapEntry === DISABLED_VOICE_MARKER) {
toastr.info(`Specified voice for ${name} was not found. Check the TTS extension settings.`);
return;
}
resetTtsPlayback()
ttsJobQueue.push({ mes: text, name: name });
await moduleWorker();
// Return back to the chat voices
await initVoiceMap(false);
}
async function moduleWorker() {
// Primarily determining when to add new chat to the TTS queue
const enabled = $('#tts_enabled').is(':checked')
@ -636,10 +667,22 @@ async function onChatChanged() {
await initVoiceMap()
}
function getCharacters(){
/**
* Get characters in current chat
* @param {boolean} unrestricted - If true, will include all characters in voiceMapEntries, even if they are not in the current chat.
* @returns {string[]} - Array of character names
*/
function getCharacters(unrestricted) {
const context = getContext()
if (unrestricted) {
const names = context.characters.map(char => char.name);
names.unshift(DEFAULT_VOICE_MARKER);
return names;
}
let characters = []
if (context.groupId === null){
if (context.groupId === null) {
// Single char chat
characters.push(DEFAULT_VOICE_MARKER)
characters.push(context.name1)
@ -651,7 +694,7 @@ function getCharacters(){
const group = context.groups.find(group => context.groupId == group.id)
for (let member of group.members) {
// Remove suffix
if (member.endsWith('.png')){
if (member.endsWith('.png')) {
member = member.slice(0, -4)
}
characters.push(member)
@ -661,15 +704,15 @@ function getCharacters(){
}
function sanitizeId(input) {
// Remove any non-alphanumeric characters except underscore (_) and hyphen (-)
let sanitized = input.replace(/[^a-zA-Z0-9-_]/g, '');
// Remove any non-alphanumeric characters except underscore (_) and hyphen (-)
let sanitized = input.replace(/[^a-zA-Z0-9-_]/g, '');
// Ensure first character is always a letter
if (!/^[a-zA-Z]/.test(sanitized)) {
sanitized = 'element_' + sanitized;
}
// Ensure first character is always a letter
if (!/^[a-zA-Z]/.test(sanitized)) {
sanitized = 'element_' + sanitized;
}
return sanitized;
return sanitized;
}
function parseVoiceMap(voiceMapString) {
@ -691,13 +734,13 @@ function parseVoiceMap(voiceMapString) {
*/
function updateVoiceMap() {
const tempVoiceMap = {}
for (const voice of voiceMapEntries){
if (voice.voiceId === null){
for (const voice of voiceMapEntries) {
if (voice.voiceId === null) {
continue
}
tempVoiceMap[voice.name] = voice.voiceId
}
if (Object.keys(tempVoiceMap).length !== 0){
if (Object.keys(tempVoiceMap).length !== 0) {
voiceMap = tempVoiceMap
console.log(`Voicemap updated to ${JSON.stringify(voiceMap)}`)
}
@ -712,13 +755,13 @@ class VoiceMapEntry {
name
voiceId
selectElement
constructor (name, voiceId=DEFAULT_VOICE_MARKER) {
constructor(name, voiceId = DEFAULT_VOICE_MARKER) {
this.name = name
this.voiceId = voiceId
this.selectElement = null
}
addUI(voiceIds){
addUI(voiceIds) {
let sanitizedName = sanitizeId(this.name)
let defaultOption = this.name === DEFAULT_VOICE_MARKER ?
`<option>${DISABLED_VOICE_MARKER}</option>` :
@ -734,7 +777,7 @@ class VoiceMapEntry {
$('#tts_voicemap_block').append(template)
// Populate voice ID select list
for (const voiceId of voiceIds){
for (const voiceId of voiceIds) {
const option = document.createElement('option');
option.innerText = voiceId.name;
option.value = voiceId.name;
@ -754,12 +797,12 @@ class VoiceMapEntry {
/**
* Init voiceMapEntries for character select list.
*
* @param {boolean} unrestricted - If true, will include all characters in voiceMapEntries, even if they are not in the current chat.
*/
export async function initVoiceMap(){
export async function initVoiceMap(unrestricted = false) {
// Gate initialization if not enabled or TTS Provider not ready. Prevents error popups.
const enabled = $('#tts_enabled').is(':checked')
if (!enabled){
if (!enabled) {
return
}
@ -779,16 +822,16 @@ export async function initVoiceMap(){
voiceMapEntries = []
// Get characters in current chat
const characters = getCharacters()
const characters = getCharacters(unrestricted);
// Get saved voicemap from provider settings, handling new and old representations
let voiceMapFromSettings = {}
if ("voiceMap" in extension_settings.tts[ttsProviderName]) {
// Handle previous representation
if (typeof extension_settings.tts[ttsProviderName].voiceMap === "string"){
if (typeof extension_settings.tts[ttsProviderName].voiceMap === "string") {
voiceMapFromSettings = parseVoiceMap(extension_settings.tts[ttsProviderName].voiceMap)
// Handle new representation
} else if (typeof extension_settings.tts[ttsProviderName].voiceMap === "object"){
// Handle new representation
} else if (typeof extension_settings.tts[ttsProviderName].voiceMap === "object") {
voiceMapFromSettings = extension_settings.tts[ttsProviderName].voiceMap
}
}
@ -803,13 +846,13 @@ export async function initVoiceMap(){
}
// Build UI using VoiceMapEntry objects
for (const character of characters){
if (character === "SillyTavern System"){
for (const character of characters) {
if (character === "SillyTavern System") {
continue
}
// Check provider settings for voiceIds
let voiceId
if (character in voiceMapFromSettings){
if (character in voiceMapFromSettings) {
voiceId = voiceMapFromSettings[character]
} else if (character === DEFAULT_VOICE_MARKER) {
voiceId = DISABLED_VOICE_MARKER
@ -904,4 +947,5 @@ $(document).ready(function () {
eventSource.on(event_types.MESSAGE_SWIPED, resetTtsPlayback);
eventSource.on(event_types.CHAT_CHANGED, onChatChanged)
eventSource.on(event_types.GROUP_UPDATED, onChatChanged)
registerSlashCommand('speak', onNarrateText, ['narrate', 'tts'], `<span class="monospace">(text)</span> – narrate any text using currently selected character's voice. Use voice="Character Name" argument to set other voice from the voice map, example: <tt>/speak voice="Donald Duck" Quack!</tt>`, true, true);
})

20
public/scripts/extensions/tts/system.js
View File

@ -146,8 +146,8 @@ class SystemTtsProvider {
$('#system_tts_pitch').val(this.settings.pitch || this.defaultSettings.pitch);
// Trigger updates
$('#system_tts_rate').on("input", () =>{this.onSettingsChange()})
$('#system_tts_rate').on("input", () => {this.onSettingsChange()})
$('#system_tts_rate').on("input", () => { this.onSettingsChange() })
$('#system_tts_rate').on("input", () => { this.onSettingsChange() })
$('#system_tts_pitch_output').text(this.settings.pitch);
$('#system_tts_rate_output').text(this.settings.rate);
@ -155,7 +155,7 @@ class SystemTtsProvider {
}
// Perform a simple readiness check by trying to fetch voiceIds
async checkReady(){
async checkReady() {
await this.fetchTtsVoiceObjects()
}
@ -171,10 +171,16 @@ class SystemTtsProvider {
return [];
}
return speechSynthesis
.getVoices()
.sort((a, b) => a.lang.localeCompare(b.lang) || a.name.localeCompare(b.name))
.map(x => ({ name: x.name, voice_id: x.voiceURI, preview_url: false, lang: x.lang }));
return new Promise((resolve) => {
setTimeout(() => {
const voices = speechSynthesis
.getVoices()
.sort((a, b) => a.lang.localeCompare(b.lang) || a.name.localeCompare(b.name))
.map(x => ({ name: x.name, voice_id: x.voiceURI, preview_url: false, lang: x.lang }));
resolve(voices);
}, 1);
});
}
previewTtsVoice(voiceId) {

3
public/scripts/slash-commands.js
View File

@ -82,7 +82,8 @@ class SlashCommandParser {
if (equalsIndex !== -1) {
const key = arg.substring(0, equalsIndex);
const value = arg.substring(equalsIndex + 1);
argObj[key] = value;
// Replace "wrapping quotes" used for escaping spaces
argObj[key] = value.replace(/(^")|("$)/g, '');
}
else {
break;