feat: integrate Silero TTS as default TTS engine

- Add SileroTTS service with GPU/CPU support
- Update TTS API to support configurable engines (silero/edge)
- Add TTS_ENGINE and SILERO_SPEAKER config options
- Set Silero as default TTS engine
- Update requirements.txt with silero dependency

app/api/tts.py

@@ -7,6 +7,7 @@ from flask import current_app, request, send_file
 from flask_restx import Namespace, Resource, fields
 from app.models.voice import Voice
 from app.services.edge_tts_service import EdgeTTSService
+from app.services.silero_tts_service import SileroTTSService
 from app.services.seed_vc_service import SeedVCService
 
 logger = logging.getLogger(__name__)
@@ -110,10 +111,17 @@ class TTS(Resource):
         final_output = os.path.join(output_dir, f"{output_id}_converted.wav")
         
         try:
-            # Step 1: Generate TTS with Edge-TTS
-            logger.info("Step 1: Generating TTS with Edge-TTS")
-            edge_tts_voice = current_app.config['EDGE_TTS_VOICE']
-            tts_service = EdgeTTSService(voice=edge_tts_voice)
+            # Step 1: Generate TTS
+            tts_engine = current_app.config.get('TTS_ENGINE', 'silero')
+            logger.info(f"Step 1: Generating TTS with {tts_engine}")
+            
+            if tts_engine == 'silero':
+                silero_speaker = current_app.config.get('SILERO_SPEAKER', 'v5_ru')
+                tts_service = SileroTTSService(speaker=silero_speaker)
+            else:
+                edge_tts_voice = current_app.config['EDGE_TTS_VOICE']
+                tts_service = EdgeTTSService(voice=edge_tts_voice)
+            
             tts_service.text_to_speech(text, tts_output, speed=speed)
             
             # Step 2: Convert voice with Seed-VC