Task 19: Update TTS generation endpoint to accept edited scripts

- Modified TTSRequest to accept optional segments array
- Updated generate_audiobook endpoint to use segments if provided
- Added generate_audiobook_from_segments method to TTSService
- Ensured backward compatibility with text-based generation
- Added comprehensive tests for segment-based generation
- All tests passing (7/7)

Requirements: 15.7

backend/services/tts_service.py

@@ -404,3 +404,66 @@ class TTSService:
         
         logger.info(f"Generated audiobook: {len(audio_bytes)} bytes")
         return audio_bytes
+
+    async def generate_audiobook_from_segments(
+        self,
+        segments: List[Tuple[str, str]],
+        lang: str,
+        role_voice_map: Dict[str, str],
+        speed: float = 1.0
+    ) -> bytes:
+        """
+        Generates audiobook from pre-segmented script with speaker assignments.
+        
+        This method is used when the user has reviewed and edited the script,
+        bypassing automatic segmentation.
+        
+        Args:
+            segments: List of (speaker_name, text_content) tuples
+            lang: Language code
+            role_voice_map: Role to voice ID mapping
+            speed: Playback speed
+            
+        Returns:
+            Audio data as bytes (WAV format)
+            
+        Raises:
+            ValueError: If segments is empty or invalid
+        """
+        logger.info(
+            f"Generating audiobook from {len(segments)} edited segments: "
+            f"lang={lang}, speed={speed}, roles={len(role_voice_map)}"
+        )
+        
+        if not segments:
+            raise ValueError("No segments provided for synthesis")
+        
+        # Get or create pipeline for language
+        pipeline = self.get_pipeline(lang)
+        
+        # Convert segments to format with voice assignments
+        segments_with_voice = []
+        for speaker, text in segments:
+            voice = role_voice_map.get(speaker, self.DEFAULT_VOICE)
+            segments_with_voice.append((speaker, voice, text))
+        
+        logger.info(f"Processing {len(segments_with_voice)} segments with voice assignments")
+        
+        # Synthesize each segment
+        audio_segments = []
+        for role_id, voice, content in segments_with_voice:
+            logger.debug(f"Synthesizing segment for role '{role_id}' with voice '{voice}'")
+            audio = self.synthesize_segment(pipeline, content, voice, speed)
+            audio_segments.append(audio)
+        
+        # Concatenate all audio
+        final_audio = self.concatenate_audio(audio_segments)
+        
+        # Convert to bytes (WAV format)
+        buffer = io.BytesIO()
+        sf.write(buffer, final_audio, self.SAMPLE_RATE, format='WAV')
+        buffer.seek(0)
+        audio_bytes = buffer.read()
+        
+        logger.info(f"Generated audiobook from edited segments: {len(audio_bytes)} bytes")
+        return audio_bytes