feat: podcast demo mode with ALWRITY_ENABLED_FEATURES support

- Add ALWRITY_ENABLED_FEATURES env var for feature gating
- Podcast-only mode: skip LLM bootstrap, scheduler, persona services
- Enhance video generation prompt with scene context, analysis, narration
- Add voice cloning support via custom_voice_id in WaveSpeed
- Add text-to-speech for research results (browser speechSynthesis)
- Fix render queue to sync images from script phase
- Add WaveSpeed LLM pricing (gpt-oss-120b)
- Fix podcast bible generation error handling
- Refactor RouterManager for feature-based router loading

frontend/src/api/brandAssets.ts

@@ -14,6 +14,7 @@ export interface AssetResponse {
 export interface VoiceCloneResponse {
   success: boolean;
   custom_voice_id?: string;
+  voice_name?: string;
   preview_audio_url?: string;
   asset_id?: number;
   message?: string;