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/main.py

@@ -56,7 +56,8 @@ class RoleVoiceMapping(BaseModel):
 
 class TTSRequest(BaseModel):
     """Request model for TTS generation endpoint."""
-    text: str = Field(..., description="Text to convert to speech")
+    segments: Optional[List[ScriptSegment]] = Field(None, description="Optional edited script segments")
+    text: Optional[str] = Field(None, description="Text to convert to speech (used if segments not provided)")
     lang: str = Field(..., description="Language code (a, b, f, j)")
     roles: List[RoleVoiceMapping] = Field(..., description="Role to voice mappings")
     speed: Optional[float] = Field(1.0, description="Playback speed (0.5-1.5)")
@@ -253,11 +254,24 @@ async def generate_audiobook(request: TTSRequest):
     """
     logger.info(
         f"Audio generation requested: lang={request.lang}, "
-        f"roles={len(request.roles)}, speed={request.speed}"
+        f"roles={len(request.roles)}, speed={request.speed}, "
+        f"segments={len(request.segments) if request.segments else 0}"
     )
     
-    # Validate required fields (Pydantic handles basic validation)
-    if not request.text or not request.text.strip():
+    # Validate that either segments or text is provided
+    if not request.segments and not request.text:
+        logger.error("Neither segments nor text provided")
+        return JSONResponse(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            content={
+                "error": "ValidationError",
+                "message": "Either segments or text must be provided",
+                "details": {"fields": ["segments", "text"]}
+            }
+        )
+    
+    # Validate text if provided and no segments
+    if not request.segments and request.text and not request.text.strip():
         logger.error("Empty text provided")
         return JSONResponse(
             status_code=status.HTTP_400_BAD_REQUEST,
@@ -316,13 +330,23 @@ async def generate_audiobook(request: TTSRequest):
     role_voice_map = {role.id: role.voice for role in request.roles}
     
     try:
-        # Generate audiobook
-        audio_bytes = await tts_service.generate_audiobook(
-            text=request.text,
-            lang=request.lang,
-            role_voice_map=role_voice_map,
-            speed=request.speed
-        )
+        # Generate audiobook using segments if provided, otherwise use text
+        if request.segments:
+            logger.info(f"Generating audiobook from {len(request.segments)} edited segments")
+            audio_bytes = await tts_service.generate_audiobook_from_segments(
+                segments=[(seg.speaker, seg.text) for seg in request.segments],
+                lang=request.lang,
+                role_voice_map=role_voice_map,
+                speed=request.speed
+            )
+        else:
+            logger.info("Generating audiobook from text with automatic segmentation")
+            audio_bytes = await tts_service.generate_audiobook(
+                text=request.text,
+                lang=request.lang,
+                role_voice_map=role_voice_map,
+                speed=request.speed
+            )
         
         # Create streaming response with proper headers
         return StreamingResponse(