fix(voice): expose TTS format in user settings

src/components/settings/view/tabs/VoiceSettingsTab.tsx

@@ -54,7 +54,7 @@ export default function VoiceSettingsTab() {
             value={config.apiKey}
             onChange={(e) => update({ apiKey: e.target.value })}
           />
-          <div className="grid grid-cols-1 gap-4 sm:grid-cols-3">
+          <div className="grid grid-cols-1 gap-4 sm:grid-cols-4">
             <Field
               label={t('voiceSettings.sttModel')}
               placeholder="whisper-1"
@@ -73,6 +73,12 @@ export default function VoiceSettingsTab() {
               value={config.ttsVoice}
               onChange={(e) => update({ ttsVoice: e.target.value })}
             />
+            <Field
+              label={t('voiceSettings.format')}
+              placeholder="mp3"
+              value={config.ttsFormat}
+              onChange={(e) => update({ ttsFormat: e.target.value })}
+            />
           </div>
           <p className="text-xs text-muted-foreground">{t('voiceSettings.note')}</p>
         </div>

src/hooks/useVoiceConfig.ts

@@ -6,17 +6,20 @@ export type VoiceConfig = {
   sttModel: string;
   ttsModel: string;
   ttsVoice: string;
+  ttsFormat: string;
 };
 
 const STORAGE_KEY = 'voiceConfig';
-const DEFAULTS: VoiceConfig = { baseUrl: '', apiKey: '', sttModel: '', ttsModel: '', ttsVoice: '' };
+const DEFAULTS: VoiceConfig = { baseUrl: '', apiKey: '', sttModel: '', ttsModel: '', ttsVoice: '', ttsFormat: 'mp3' };
 
 function read(): VoiceConfig {
   try {
     const raw = localStorage.getItem(STORAGE_KEY);
     if (!raw) return { ...DEFAULTS };
     const parsed = JSON.parse(raw);
-    return { ...DEFAULTS, ...(parsed && typeof parsed === 'object' ? parsed : {}) };
+    const next = { ...DEFAULTS, ...(parsed && typeof parsed === 'object' ? parsed : {}) };
+    if (!next.ttsFormat) next.ttsFormat = DEFAULTS.ttsFormat;
+    return next;
   } catch {
     return { ...DEFAULTS };
   }
@@ -33,6 +36,7 @@ export function voiceConfigHeaders(): Record<string, string> {
   if (c.sttModel) h['x-voice-stt-model'] = c.sttModel;
   if (c.ttsModel) h['x-voice-tts-model'] = c.ttsModel;
   if (c.ttsVoice) h['x-voice-tts-voice'] = c.ttsVoice;
+  if (c.ttsFormat) h['x-voice-tts-format'] = c.ttsFormat;
   return h;
 }
 

src/i18n/locales/en/settings.json

@@ -61,7 +61,8 @@
     "sttModel": "Speech-to-text model",
     "ttsModel": "Text-to-speech model",
     "voice": "Voice",
-    "note": "The shown defaults work with OpenAI once you add a key. For other providers, set the base URL and model names to match."
+    "format": "Audio format",
+    "note": "The shown defaults work with OpenAI once you add a key. For other providers, set the base URL, model names, and audio format to match."
   },
   "quickSettings": {
     "title": "Quick Settings",