Update app.py

app.py

@@ -1,14 +1,16 @@
 from fastapi import FastAPI, HTTPException, Request
-from fastapi.responses import FileResponse, JSONResponse
-from fastapi.staticfiles import StaticFiles
+from fastapi.responses import JSONResponse, StreamingResponse
 from google import genai
 from google.genai import types
 import wave
+import io
 import os
-import uuid
 from typing import Optional
 from pydantic import BaseModel
-from pathlib import Path
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
 
 app = FastAPI(
     title="Google GenAI TTS API",
@@ -18,13 +20,6 @@ app = FastAPI(
     redoc_url=None
 )
 
-# Configuration
-AUDIO_OUTPUT_DIR = "audio_output"
-Path(AUDIO_OUTPUT_DIR).mkdir(exist_ok=True)
-
-# Mount static files for Hugging Face Spaces
-app.mount("/static", StaticFiles(directory="static"), name="static")
-
 class TTSRequest(BaseModel):
     text: str
     voice_name: Optional[str] = "Kore"
@@ -40,13 +35,15 @@ def initialize_genai_client():
         raise ValueError("GEMINI_API_KEY environment variable not set")
     return genai.Client(api_key=api_key)
 
-def generate_wave_file(filename: str, pcm_data: bytes, channels: int, rate: int, sample_width: int):
-    """Generate a WAV file from PCM data"""
-    with wave.open(filename, "wb") as wf:
-        wf.setnchannels(channels)
-        wf.setsampwidth(sample_width)
-        wf.setframerate(rate)
-        wf.writeframes(pcm_data)
+def generate_wave_bytes(pcm_data: bytes, channels: int, rate: int, sample_width: int) -> bytes:
+    """Generate WAV file bytes from PCM data"""
+    with io.BytesIO() as wav_buffer:
+        with wave.open(wav_buffer, "wb") as wf:
+            wf.setnchannels(channels)
+            wf.setsampwidth(sample_width)
+            wf.setframerate(rate)
+            wf.writeframes(pcm_data)
+        return wav_buffer.getvalue()
 
 @app.post("/api/generate-tts/")
 async def generate_tts(request: TTSRequest):
@@ -62,7 +59,7 @@ async def generate_tts(request: TTSRequest):
     - sample_width: Sample width in bytes (default: 2)
     
     Returns:
-    - JSON with file URL or error message
+    - StreamingResponse with the WAV audio file
     """
     try:
         client = initialize_genai_client()
@@ -89,26 +86,20 @@ async def generate_tts(request: TTSRequest):
         
         audio_data = response.candidates[0].content.parts[0].inline_data.data
         
-        file_name = f"tts_{uuid.uuid4().hex}.wav"
-        file_path = os.path.join(AUDIO_OUTPUT_DIR, file_name)
-        
-        generate_wave_file(
-            file_path,
+        wav_bytes = generate_wave_bytes(
             audio_data,
             channels=request.channels,
             rate=request.sample_rate,
             sample_width=request.sample_width
         )
         
-        # For Hugging Face Spaces, we need to return the URL where the file can be accessed
-        file_url = f"/static/{file_name}"
-        os.rename(file_path, f"static/{file_name}")
-        
-        return JSONResponse({
-            "status": "success",
-            "audio_url": file_url,
-            "filename": file_name
-        })
+        return StreamingResponse(
+            io.BytesIO(wav_bytes),
+            media_type="audio/wav",
+            headers={
+                "Content-Disposition": f"attachment; filename=generated_audio.wav"
+            }
+        )
         
     except Exception as e:
         return JSONResponse(
@@ -120,13 +111,9 @@ async def generate_tts(request: TTSRequest):
 async def root():
     return {"message": "Google GenAI TTS API is running"}
 
-# Error handler
-@app.exception_handler(Exception)
-async def generic_exception_handler(request: Request, exc: Exception):
-    return JSONResponse(
-        status_code=500,
-        content={"message": f"An error occurred: {str(exc)}"}
-    )
+@app.get("/health")
+async def health_check():
+    return {"status": "healthy"}
 
 if __name__ == "__main__":
     import uvicorn