Added regex filter option to TTS extension (#4924) * Add regex filter option to TTS extension - Added checkbox to enable/disable regex filtering of TTS text - Added text input for custom regex patterns - Default pattern removes emojis and non-English text while preserving letters, numbers, spaces, and punctuation - Regex is applied after asterisk removal and other text processing - Includes error handling for invalid regex patterns - Automatically cleans up extra spaces after regex removal * reverted the accidental change in tts_skip_tags description clarified the regex description * Add regex validation warning to TTS settings * fixed regex field in UI * reworked the regex warning * changed the regex event to change (input might not have worked correctly) * Apply review comments * Spacing fix --------- Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>

ef89d0f291a788ba1529cb009bdc988c452ec5d8

ZhenyaPav <61346893+ZhenyaPav@users.noreply.github.com>

Signed

public/scripts/extensions/tts/index.js+49 -1 Viewed

 import { cancelTtsPlay, eventSource, event_types, getCurrentChatId, isStreamingEnabled, name2, saveSettingsDebounced, substituteParams } from '../../../script.js';
 import { ModuleWorkerWrapper, extension_settings, getContext, renderExtensionTemplateAsync } from '../../extensions.js';
-import { delay, escapeRegex, getBase64Async, getStringHash, onlyUnique } from '../../utils.js';
+import { delay, escapeRegex, getBase64Async, getStringHash, onlyUnique, regexFromString } from '../../utils.js';
 import { EdgeTtsProvider } from './edge.js';
 import { ElevenLabsTtsProvider } from './elevenlabs.js';
 import { SileroTtsProvider } from './silerotts.js';

             : text.replaceAll('*', '').trim(); // remove just the asterisks
+    }
+    if (extension_settings.tts.apply_regex && extension_settings.tts.regex_pattern) {
+        const regex = regexFromString(extension_settings.tts.regex_pattern);
+        if (regex) {
+            // Clean up extra spaces that might be left after removal
+            text = text.replace(regex, '').replace(/\s+/g, ' ').trim();
+        } else {
+            console.warn('Invalid regex pattern:', extension_settings.tts.regex_pattern);
+        }
+    }
     if (extension_settings.tts.narrate_quoted_only) {
         const partJoiner = (ttsProvider?.separator || ' ... ');
         text = joinQuotedBlocks(text, { separator: partJoiner, includeQuotes: true });

     $('#tts_skip_codeblocks').prop('checked', extension_settings.tts.skip_codeblocks);
     $('#tts_skip_tags').prop('checked', extension_settings.tts.skip_tags);
     $('#tts_multi_voice_enabled').prop('checked', extension_settings.tts.multi_voice_enabled);
+    $('#tts_apply_regex').prop('checked', extension_settings.tts.apply_regex);
+    $('#tts_regex_pattern').val(extension_settings.tts.regex_pattern);
+    $('#tts_regex_block').toggle(extension_settings.tts.apply_regex);
+    updateRegexPatternWarning();
     $('#playback_rate').val(extension_settings.tts.playback_rate);
     $('#playback_rate_counter').val(Number(extension_settings.tts.playback_rate).toFixed(2));
     $('#playback_rate_block').toggle(extension_settings.tts.currentProvider !== 'System');

     narrate_user: false,
     playback_rate: 1,
     multi_voice_enabled: false,
+    apply_regex: false,
+    regex_pattern: '',
 };
 function setTtsStatus(status, success) {

     initVoiceMap();
+}
+function onApplyRegexChange() {
+    extension_settings.tts.apply_regex = !!$('#tts_apply_regex').prop('checked');
+    saveSettingsDebounced();
+    $('#tts_regex_block').toggle(extension_settings.tts.apply_regex);
+    updateRegexPatternWarning();
+}
+function onRegexPatternChange() {
+    extension_settings.tts.regex_pattern = $('#tts_regex_pattern').val().toString();
+    saveSettingsDebounced();
+    updateRegexPatternWarning();
+}
+function updateRegexPatternWarning() {
+    const warning = $('#tts_regex_warning');
+    if (!extension_settings.tts.apply_regex) {
+        warning.hide();
+        return;
+    }
+    const pattern = extension_settings.tts.regex_pattern;
+    if (!pattern) {
+        warning.hide();
+        return;
+    }
+    const regex = regexFromString(pattern);
+    warning.toggle(!regex);
+}
 //##############//
 // TTS Provider //
 //##############//

         $('#tts_narrate_by_paragraphs').on('click', onNarrateByParagraphsClick);
         $('#tts_narrate_user').on('click', onNarrateUserClick);
         $('#tts_multi_voice_enabled').on('click', onMultiVoiceClick);
+        $('#tts_apply_regex').on('change', onApplyRegexChange);
+        $('#tts_regex_pattern').on('input', onRegexPatternChange);
         $('#playback_rate').on('input', function () {
             const value = $(this).val();

public/scripts/extensions/tts/settings.html+11 -0 Viewed

                         Different voices for "quotes", *text inside asterisks* and other text
                     </small>
                 </label>
+                <label class="checkbox_label" for="tts_apply_regex" title="Applies the regex pattern to filter text before TTS.">
+                    <input type="checkbox" id="tts_apply_regex">
+                    <small data-i18n="Apply regex filter">Apply regex filter to text</small>
+                </label>
+                <div id="tts_regex_block" class="marginTop5">
+                    <div class="range-block-title justifyLeft">
+                        <small data-i18n="Regex Pattern">Regex Pattern (removes matching text)</small>
+                    </div>
+                    <input type="text" id="tts_regex_pattern" class="text_pole width100p" placeholder="Example: /[^a-zA-Z0-9\s.,!?;:'&quot;()]+/g" />
+                    <small id="tts_regex_warning" class="warning" data-i18n="Invalid regex pattern.">Invalid regex pattern.</small>
+                </div>
             </div>
             <div id="playback_rate_block" class="range-block">
                 <hr>