mirror of
https://github.com/SillyTavern/SillyTavern.git
synced 2025-06-05 21:59:27 +02:00
Merge branch 'SillyTavern:release' into release
This commit is contained in:
erew123
GitHub
@ -310,12 +310,12 @@ class CoquiTtsProvider {
|
||||
modelDict = coquiApiModelsFull;
|
||||
|
||||
if (model_setting_language == null & 'languages' in modelDict[model_language][model_dataset][model_label]) {
|
||||
toastr.error('Model language not selected, please select one.', DEBUG_PREFIX+' voice mapping model language', { timeOut: 10000, extendedTimeOut: 20000, preventDuplicates: true });
|
||||
toastr.error('Model language not selected, please select one.', DEBUG_PREFIX + ' voice mapping model language', { timeOut: 10000, extendedTimeOut: 20000, preventDuplicates: true });
|
||||
return;
|
||||
}
|
||||
|
||||
if (model_setting_speaker == null & 'speakers' in modelDict[model_language][model_dataset][model_label]) {
|
||||
toastr.error('Model speaker not selected, please select one.', DEBUG_PREFIX+' voice mapping model speaker', { timeOut: 10000, extendedTimeOut: 20000, preventDuplicates: true });
|
||||
toastr.error('Model speaker not selected, please select one.', DEBUG_PREFIX + ' voice mapping model speaker', { timeOut: 10000, extendedTimeOut: 20000, preventDuplicates: true });
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
import { callPopup, cancelTtsPlay, eventSource, event_types, name2, saveSettingsDebounced } from '../../../script.js';
|
||||
import { ModuleWorkerWrapper, doExtrasFetch, extension_settings, getApiUrl, getContext, modules } from '../../extensions.js';
|
||||
import { delay, escapeRegex, getStringHash } from '../../utils.js';
|
||||
import { delay, escapeRegex, getBase64Async, getStringHash, onlyUnique } from '../../utils.js';
|
||||
import { EdgeTtsProvider } from './edge.js';
|
||||
import { ElevenLabsTtsProvider } from './elevenlabs.js';
|
||||
import { SileroTtsProvider } from './silerotts.js';
|
||||
@ -318,12 +318,14 @@ async function playAudioData(audioBlob) {
|
||||
if (currentAudioJob == null) {
|
||||
console.log('Cancelled TTS playback because currentAudioJob was null');
|
||||
}
|
||||
const reader = new FileReader();
|
||||
reader.onload = function (e) {
|
||||
const srcUrl = e.target.result;
|
||||
if (audioBlob instanceof Blob) {
|
||||
const srcUrl = await getBase64Async(audioBlob);
|
||||
audioElement.src = srcUrl;
|
||||
};
|
||||
reader.readAsDataURL(audioBlob);
|
||||
} else if (typeof audioBlob === 'string') {
|
||||
audioElement.src = audioBlob;
|
||||
} else {
|
||||
throw `TTS received invalid audio data type ${typeof audioBlob}`;
|
||||
}
|
||||
audioElement.addEventListener('ended', completeCurrentAudioJob);
|
||||
audioElement.addEventListener('canplay', () => {
|
||||
console.debug('Starting TTS playback');
|
||||
@ -419,11 +421,15 @@ function completeCurrentAudioJob() {
|
||||
* @param {Response} response
|
||||
*/
|
||||
async function addAudioJob(response) {
|
||||
const audioData = await response.blob();
|
||||
if (!audioData.type.startsWith('audio/')) {
|
||||
throw `TTS received HTTP response with invalid data format. Expecting audio/*, got ${audioData.type}`;
|
||||
if (typeof response === 'string') {
|
||||
audioJobQueue.push(response);
|
||||
} else {
|
||||
const audioData = await response.blob();
|
||||
if (!audioData.type.startsWith('audio/')) {
|
||||
throw `TTS received HTTP response with invalid data format. Expecting audio/*, got ${audioData.type}`;
|
||||
}
|
||||
audioJobQueue.push(audioData);
|
||||
}
|
||||
audioJobQueue.push(audioData);
|
||||
console.debug('Pushed audio job to queue.');
|
||||
}
|
||||
|
||||
@ -434,7 +440,7 @@ async function processAudioJobQueue() {
|
||||
}
|
||||
try {
|
||||
audioQueueProcessorReady = false;
|
||||
currentAudioJob = audioJobQueue.pop();
|
||||
currentAudioJob = audioJobQueue.shift();
|
||||
playAudioData(currentAudioJob);
|
||||
talkingAnimation(true);
|
||||
} catch (error) {
|
||||
@ -465,13 +471,25 @@ function saveLastValues() {
|
||||
}
|
||||
|
||||
async function tts(text, voiceId, char) {
|
||||
async function processResponse(response) {
|
||||
// RVC injection
|
||||
if (extension_settings.rvc.enabled && typeof window['rvcVoiceConversion'] === 'function')
|
||||
response = await window['rvcVoiceConversion'](response, char, text);
|
||||
|
||||
await addAudioJob(response);
|
||||
}
|
||||
|
||||
let response = await ttsProvider.generateTts(text, voiceId);
|
||||
|
||||
// RVC injection
|
||||
if (extension_settings.rvc.enabled && typeof window['rvcVoiceConversion'] === 'function')
|
||||
response = await window['rvcVoiceConversion'](response, char, text);
|
||||
// If async generator, process every chunk as it comes in
|
||||
if (typeof response[Symbol.asyncIterator] === 'function') {
|
||||
for await (const chunk of response) {
|
||||
await processResponse(chunk);
|
||||
}
|
||||
} else {
|
||||
await processResponse(response);
|
||||
}
|
||||
|
||||
addAudioJob(response);
|
||||
completeTtsJob();
|
||||
}
|
||||
|
||||
@ -746,7 +764,7 @@ function getCharacters(unrestricted) {
|
||||
if (unrestricted) {
|
||||
const names = context.characters.map(char => char.name);
|
||||
names.unshift(DEFAULT_VOICE_MARKER);
|
||||
return names;
|
||||
return names.filter(onlyUnique);
|
||||
}
|
||||
|
||||
let characters = [];
|
||||
@ -761,14 +779,13 @@ function getCharacters(unrestricted) {
|
||||
characters.push(context.name1);
|
||||
const group = context.groups.find(group => context.groupId == group.id);
|
||||
for (let member of group.members) {
|
||||
// Remove suffix
|
||||
if (member.endsWith('.png')) {
|
||||
member = member.slice(0, -4);
|
||||
const character = context.characters.find(char => char.avatar == member);
|
||||
if (character) {
|
||||
characters.push(character.name);
|
||||
}
|
||||
characters.push(member);
|
||||
}
|
||||
}
|
||||
return characters;
|
||||
return characters.filter(onlyUnique);
|
||||
}
|
||||
|
||||
function sanitizeId(input) {
|
||||
|
||||
@ -1,4 +1,5 @@
|
||||
import { getRequestHeaders, callPopup } from '../../../script.js';
|
||||
import { splitRecursive } from '../../utils.js';
|
||||
import { getPreviewString, saveTtsProviderSettings } from './index.js';
|
||||
import { initVoiceMap } from './index.js';
|
||||
|
||||
@ -52,7 +53,7 @@ class NovelTtsProvider {
|
||||
|
||||
|
||||
// Add a new Novel custom voice to provider
|
||||
async addCustomVoice(){
|
||||
async addCustomVoice() {
|
||||
const voiceName = await callPopup('<h3>Custom Voice name:</h3>', 'input');
|
||||
this.settings.customVoices.push(voiceName);
|
||||
this.populateCustomVoices();
|
||||
@ -74,7 +75,7 @@ class NovelTtsProvider {
|
||||
}
|
||||
|
||||
// Create the UI dropdown list of voices in provider
|
||||
populateCustomVoices(){
|
||||
populateCustomVoices() {
|
||||
let voiceSelect = $('#tts-novel-custom-voices-select');
|
||||
voiceSelect.empty();
|
||||
this.settings.customVoices.forEach(voice => {
|
||||
@ -88,7 +89,7 @@ class NovelTtsProvider {
|
||||
console.info('Using default TTS Provider settings');
|
||||
}
|
||||
$('#tts-novel-custom-voices-add').on('click', () => (this.addCustomVoice()));
|
||||
$('#tts-novel-custom-voices-delete').on('click',() => (this.deleteCustomVoice()));
|
||||
$('#tts-novel-custom-voices-delete').on('click', () => (this.deleteCustomVoice()));
|
||||
|
||||
// Only accept keys defined in defaultSettings
|
||||
this.settings = this.defaultSettings;
|
||||
@ -108,7 +109,7 @@ class NovelTtsProvider {
|
||||
|
||||
// Perform a simple readiness check by trying to fetch voiceIds
|
||||
// Doesnt really do much for Novel, not seeing a good way to test this at the moment.
|
||||
async checkReady(){
|
||||
async checkReady() {
|
||||
await this.fetchTtsVoiceObjects();
|
||||
}
|
||||
|
||||
@ -179,22 +180,26 @@ class NovelTtsProvider {
|
||||
this.audioElement.play();
|
||||
}
|
||||
|
||||
async fetchTtsGeneration(inputText, voiceId) {
|
||||
async* fetchTtsGeneration(inputText, voiceId) {
|
||||
const MAX_LENGTH = 1000;
|
||||
console.info(`Generating new TTS for voice_id ${voiceId}`);
|
||||
const response = await fetch('/api/novelai/generate-voice',
|
||||
{
|
||||
method: 'POST',
|
||||
headers: getRequestHeaders(),
|
||||
body: JSON.stringify({
|
||||
'text': inputText,
|
||||
'voice': voiceId,
|
||||
}),
|
||||
},
|
||||
);
|
||||
if (!response.ok) {
|
||||
toastr.error(response.statusText, 'TTS Generation Failed');
|
||||
throw new Error(`HTTP ${response.status}: ${await response.text()}`);
|
||||
const chunks = splitRecursive(inputText, MAX_LENGTH);
|
||||
for (const chunk of chunks) {
|
||||
const response = await fetch('/api/novelai/generate-voice',
|
||||
{
|
||||
method: 'POST',
|
||||
headers: getRequestHeaders(),
|
||||
body: JSON.stringify({
|
||||
'text': chunk,
|
||||
'voice': voiceId,
|
||||
}),
|
||||
},
|
||||
);
|
||||
if (!response.ok) {
|
||||
toastr.error(response.statusText, 'TTS Generation Failed');
|
||||
throw new Error(`HTTP ${response.status}: ${await response.text()}`);
|
||||
}
|
||||
yield response;
|
||||
}
|
||||
return response;
|
||||
}
|
||||
}
|
||||
|
||||
@ -51,7 +51,16 @@ class XTTSTtsProvider {
|
||||
defaultSettings = {
|
||||
provider_endpoint: 'http://localhost:8020',
|
||||
language: 'en',
|
||||
temperature: 0.75,
|
||||
length_penalty: 1.0,
|
||||
repetition_penalty: 5.0,
|
||||
top_k: 50,
|
||||
top_p: 0.85,
|
||||
speed: 1,
|
||||
enable_text_splitting: true,
|
||||
stream_chunk_size: 100,
|
||||
voiceMap: {},
|
||||
streaming: false,
|
||||
};
|
||||
|
||||
get settingsHtml() {
|
||||
@ -59,9 +68,7 @@ class XTTSTtsProvider {
|
||||
<label for="xtts_api_language">Language</label>
|
||||
<select id="xtts_api_language">`;
|
||||
|
||||
|
||||
for (let language in this.languageLabels) {
|
||||
|
||||
if (this.languageLabels[language] == this.settings?.language) {
|
||||
html += `<option value="${this.languageLabels[language]}" selected="selected">${language}</option>`;
|
||||
continue;
|
||||
@ -70,27 +77,73 @@ class XTTSTtsProvider {
|
||||
html += `<option value="${this.languageLabels[language]}">${language}</option>`;
|
||||
}
|
||||
|
||||
|
||||
html += `
|
||||
</select>
|
||||
<label">XTTS Settings:</label><br/>
|
||||
<label for="xtts_tts_endpoint">Provider Endpoint:</label>
|
||||
<input id="xtts_tts_endpoint" type="text" class="text_pole" maxlength="250" value="${this.defaultSettings.provider_endpoint}"/>
|
||||
|
||||
`;
|
||||
|
||||
html += `
|
||||
|
||||
<span>
|
||||
<span>Use <a target="_blank" href="https://github.com/daswer123/xtts-api-server">XTTSv2 TTS Server</a>.</span>
|
||||
<label for="xtts_tts_streaming" class="checkbox_label">
|
||||
<input id="xtts_tts_streaming" type="checkbox" />
|
||||
<span>Streaming <small>(RVC not supported)</small></span>
|
||||
</label>
|
||||
<label for="xtts_speed">Speed: <span id="xtts_tts_speed_output">${this.defaultSettings.speed}</span></label>
|
||||
<input id="xtts_speed" type="range" value="${this.defaultSettings.speed}" min="0.5" max="2" step="0.01" />
|
||||
|
||||
<label for="xtts_temperature">Temperature: <span id="xtts_tts_temperature_output">${this.defaultSettings.temperature}</span></label>
|
||||
<input id="xtts_temperature" type="range" value="${this.defaultSettings.temperature}" min="0.01" max="1" step="0.01" />
|
||||
|
||||
<label for="xtts_length_penalty">Length Penalty: <span id="xtts_length_penalty_output">${this.defaultSettings.length_penalty}</span></label>
|
||||
<input id="xtts_length_penalty" type="range" value="${this.defaultSettings.length_penalty}" min="0.5" max="2" step="0.1" />
|
||||
|
||||
<label for="xtts_repetition_penalty">Repetition Penalty: <span id="xtts_repetition_penalty_output">${this.defaultSettings.repetition_penalty}</span></label>
|
||||
<input id="xtts_repetition_penalty" type="range" value="${this.defaultSettings.repetition_penalty}" min="1" max="10" step="0.1" />
|
||||
|
||||
<label for="xtts_top_k">Top K: <span id="xtts_top_k_output">${this.defaultSettings.top_k}</span></label>
|
||||
<input id="xtts_top_k" type="range" value="${this.defaultSettings.top_k}" min="0" max="100" step="1" />
|
||||
|
||||
<label for="xtts_top_p">Top P: <span id="xtts_top_p_output">${this.defaultSettings.top_p}</span></label>
|
||||
<input id="xtts_top_p" type="range" value="${this.defaultSettings.top_p}" min="0" max="1" step="0.01" />
|
||||
|
||||
<label for="xtts_stream_chunk_size">Stream Chunk Size: <span id="xtts_stream_chunk_size_output">${this.defaultSettings.stream_chunk_size}</span></label>
|
||||
<input id="xtts_stream_chunk_size" type="range" value="${this.defaultSettings.stream_chunk_size}" min="100" max="400" step="1" />
|
||||
|
||||
<label for="xtts_enable_text_splitting" class="checkbox_label">
|
||||
<input id="xtts_enable_text_splitting" type="checkbox" ${this.defaultSettings.enable_text_splitting ? 'checked' : ''} />
|
||||
Enable Text Splitting
|
||||
</label>
|
||||
`;
|
||||
|
||||
return html;
|
||||
}
|
||||
|
||||
onSettingsChange() {
|
||||
// Used when provider settings are updated from UI
|
||||
this.settings.provider_endpoint = $('#xtts_tts_endpoint').val();
|
||||
this.settings.language = $('#xtts_api_language').val();
|
||||
|
||||
// Update the default TTS settings based on input fields
|
||||
this.settings.speed = $('#xtts_speed').val();
|
||||
this.settings.temperature = $('#xtts_temperature').val();
|
||||
this.settings.length_penalty = $('#xtts_length_penalty').val();
|
||||
this.settings.repetition_penalty = $('#xtts_repetition_penalty').val();
|
||||
this.settings.top_k = $('#xtts_top_k').val();
|
||||
this.settings.top_p = $('#xtts_top_p').val();
|
||||
this.settings.stream_chunk_size = $('#xtts_stream_chunk_size').val();
|
||||
this.settings.enable_text_splitting = $('#xtts_enable_text_splitting').is(':checked');
|
||||
this.settings.streaming = $('#xtts_tts_streaming').is(':checked');
|
||||
|
||||
// Update the UI to reflect changes
|
||||
$('#xtts_tts_speed_output').text(this.settings.speed);
|
||||
$('#xtts_tts_temperature_output').text(this.settings.temperature);
|
||||
$('#xtts_length_penalty_output').text(this.settings.length_penalty);
|
||||
$('#xtts_repetition_penalty_output').text(this.settings.repetition_penalty);
|
||||
$('#xtts_top_k_output').text(this.settings.top_k);
|
||||
$('#xtts_top_p_output').text(this.settings.top_p);
|
||||
$('#xtts_stream_chunk_size_output').text(this.settings.stream_chunk_size);
|
||||
|
||||
saveTtsProviderSettings();
|
||||
this.changeTTSSettings();
|
||||
}
|
||||
|
||||
async loadSettings(settings) {
|
||||
@ -121,10 +174,40 @@ class XTTSTtsProvider {
|
||||
}
|
||||
}, 2000);
|
||||
|
||||
// Set initial values from the settings
|
||||
$('#xtts_tts_endpoint').val(this.settings.provider_endpoint);
|
||||
$('#xtts_tts_endpoint').on('input', () => { this.onSettingsChange(); });
|
||||
$('#xtts_api_language').val(this.settings.language);
|
||||
$('#xtts_speed').val(this.settings.speed);
|
||||
$('#xtts_temperature').val(this.settings.temperature);
|
||||
$('#xtts_length_penalty').val(this.settings.length_penalty);
|
||||
$('#xtts_repetition_penalty').val(this.settings.repetition_penalty);
|
||||
$('#xtts_top_k').val(this.settings.top_k);
|
||||
$('#xtts_top_p').val(this.settings.top_p);
|
||||
$('#xtts_enable_text_splitting').prop('checked', this.settings.enable_text_splitting);
|
||||
$('#xtts_stream_chunk_size').val(this.settings.stream_chunk_size);
|
||||
$('#xtts_tts_streaming').prop('checked', this.settings.streaming);
|
||||
|
||||
// Update the UI to reflect changes
|
||||
$('#xtts_tts_speed_output').text(this.settings.speed);
|
||||
$('#xtts_tts_temperature_output').text(this.settings.temperature);
|
||||
$('#xtts_length_penalty_output').text(this.settings.length_penalty);
|
||||
$('#xtts_repetition_penalty_output').text(this.settings.repetition_penalty);
|
||||
$('#xtts_top_k_output').text(this.settings.top_k);
|
||||
$('#xtts_top_p_output').text(this.settings.top_p);
|
||||
$('#xtts_stream_chunk_size_output').text(this.settings.stream_chunk_size);
|
||||
|
||||
// Register input/change event listeners to update settings on user interaction
|
||||
$('#xtts_tts_endpoint').on('input', () => { this.onSettingsChange(); });
|
||||
$('#xtts_api_language').on('change', () => { this.onSettingsChange(); });
|
||||
$('#xtts_speed').on('input', () => { this.onSettingsChange(); });
|
||||
$('#xtts_temperature').on('input', () => { this.onSettingsChange(); });
|
||||
$('#xtts_length_penalty').on('input', () => { this.onSettingsChange(); });
|
||||
$('#xtts_repetition_penalty').on('input', () => { this.onSettingsChange(); });
|
||||
$('#xtts_top_k').on('input', () => { this.onSettingsChange(); });
|
||||
$('#xtts_top_p').on('input', () => { this.onSettingsChange(); });
|
||||
$('#xtts_enable_text_splitting').on('change', () => { this.onSettingsChange(); });
|
||||
$('#xtts_stream_chunk_size').on('input', () => { this.onSettingsChange(); });
|
||||
$('#xtts_tts_streaming').on('change', () => { this.onSettingsChange(); });
|
||||
|
||||
await this.checkReady();
|
||||
|
||||
@ -133,7 +216,7 @@ class XTTSTtsProvider {
|
||||
|
||||
// Perform a simple readiness check by trying to fetch voiceIds
|
||||
async checkReady() {
|
||||
await this.fetchTtsVoiceObjects();
|
||||
await Promise.allSettled([this.fetchTtsVoiceObjects(), this.changeTTSSettings()]);
|
||||
}
|
||||
|
||||
async onRefreshClick() {
|
||||
@ -174,8 +257,46 @@ class XTTSTtsProvider {
|
||||
return responseJson;
|
||||
}
|
||||
|
||||
// Each time a parameter is changed, we change the configuration
|
||||
async changeTTSSettings() {
|
||||
if (!this.settings.provider_endpoint) {
|
||||
return;
|
||||
}
|
||||
|
||||
const response = await doExtrasFetch(
|
||||
`${this.settings.provider_endpoint}/set_tts_settings`,
|
||||
{
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
'Cache-Control': 'no-cache',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
'temperature': this.settings.temperature,
|
||||
'speed': this.settings.speed,
|
||||
'length_penalty': this.settings.length_penalty,
|
||||
'repetition_penalty': this.settings.repetition_penalty,
|
||||
'top_p': this.settings.top_p,
|
||||
'top_k': this.settings.top_k,
|
||||
'enable_text_splitting': this.settings.enable_text_splitting,
|
||||
'stream_chunk_size': this.settings.stream_chunk_size,
|
||||
}),
|
||||
},
|
||||
);
|
||||
return response;
|
||||
}
|
||||
|
||||
async fetchTtsGeneration(inputText, voiceId) {
|
||||
console.info(`Generating new TTS for voice_id ${voiceId}`);
|
||||
|
||||
if (this.settings.streaming) {
|
||||
const params = new URLSearchParams();
|
||||
params.append('text', inputText);
|
||||
params.append('speaker_wav', voiceId);
|
||||
params.append('language', this.settings.language);
|
||||
return `${this.settings.provider_endpoint}/tts_stream/?${params.toString()}`;
|
||||
}
|
||||
|
||||
const response = await doExtrasFetch(
|
||||
`${this.settings.provider_endpoint}/tts_to_audio/`,
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user