Implement audio generation endpoint

- Add POST /api/tts endpoint with full request validation
- Validate text, language code, speed range, and roles list
- Integrate TTSService to generate multi-voice audiobooks
- Fix Kokoro pipeline generator handling to properly collect audio
- Stream audio response with correct Content-Type (audio/wav)
- Add Content-Disposition header with filename (audiobook.wav)
- Handle errors gracefully with appropriate HTTP status codes
- Add comprehensive test suite for endpoint validation

Requirements: 6.1, 6.7, 6.8, 9.5

backend/services/tts_service.py

@@ -185,8 +185,19 @@ class TTSService:
         for chunk in chunks:
             try:
                 # Generate audio for chunk
-                audio, _ = pipeline(chunk, voice=voice, speed=speed)
-                audio_chunks.append(audio)
+                result = pipeline(chunk, voice=voice, speed=speed)
+                # Kokoro returns a generator that yields audio arrays
+                # Collect all arrays and concatenate them
+                audio_parts = []
+                for part in result:
+                    if isinstance(part, np.ndarray):
+                        # Flatten to 1D if needed
+                        audio_parts.append(part.flatten())
+                
+                # Concatenate all parts
+                if audio_parts:
+                    audio = np.concatenate(audio_parts)
+                    audio_chunks.append(audio)
             except Exception as e:
                 logger.error(f"Error synthesizing chunk with voice {voice}: {e}")
                 raise