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

backend/services/llm_providers/main_audio_generation.py

@@ -62,6 +62,7 @@ class VoiceCloneResult:
 def generate_audio(
     text: str,
     voice_id: str = "Wise_Woman",
+    custom_voice_id: Optional[str] = None,
     speed: float = 1.0,
     volume: float = 1.0,
     pitch: float = 0.0,
@@ -173,6 +174,7 @@ def generate_audio(
             audio_bytes = client.generate_speech(
                 text=text,
                 voice_id=voice_id,
+                custom_voice_id=custom_voice_id,
                 speed=speed,
                 volume=volume,
                 pitch=pitch,