Update main.py

main.py

@@ -1,5 +1,4 @@
-from fastapi import FastAPI, File, UploadFile, HTTPException
-from fastapi.responses import JSONResponse
+from fastapi import FastAPI, UploadFile, File, HTTPException
 import speech_recognition as sr
 import os
 import uuid
@@ -11,25 +10,26 @@ os.makedirs(UPLOAD_DIR, exist_ok=True)
 
 @app.post("/voice-to-text")
 async def voice_to_text(file: UploadFile = File(...)):
-    # Check file type
+    # Check for .wav file
     if not file.filename.endswith(".wav"):
         raise HTTPException(status_code=400, detail="Only .wav files are supported")
 
     # Save uploaded file
-    temp_filename = os.path.join(UPLOAD_DIR, f"{uuid.uuid4()}.wav")
-    with open(temp_filename, "wb") as f:
+    file_path = os.path.join(UPLOAD_DIR, f"{uuid.uuid4()}.wav")
+    with open(file_path, "wb") as f:
         f.write(await file.read())
 
-    # Recognize speech
+    # Speech recognition
     recognizer = sr.Recognizer()
     try:
-        with sr.AudioFile(temp_filename) as source:
+        with sr.AudioFile(file_path) as source:
             audio_data = recognizer.record(source)
-            text = recognizer.recognize_google(audio_data)
-            return JSONResponse(content={"text": text})
+            recognized_text = recognizer.recognize_google(audio_data)
+            return {"recognized_text": recognized_text}
+
     except sr.UnknownValueError:
-        raise HTTPException(status_code=400, detail="Speech not recognized")
+        raise HTTPException(status_code=400, detail="Could not understand audio")
     except sr.RequestError as e:
-        raise HTTPException(status_code=500, detail=f"API error: {e}")
+        raise HTTPException(status_code=500, detail=f"Speech API error: {e}")
     finally:
-        os.remove(temp_filename)
+        os.remove(file_path)