Update audio.py

routes/audio.py

@@ -22,17 +22,39 @@ async def tts(text: str):
 # ------------------------
 # Speech to Text
 # ------------------------
+
+# Allowed MIME types
+ALLOWED_AUDIO_TYPES = {
+    "audio/wav",
+    "audio/x-wav",
+    "audio/mpeg",    # mp3
+    "audio/mp3",     # mp3
+    "audio/mp4",     # sometimes m4a
+    "audio/m4a"      # m4a
+}
+
 @router.post("/stt")
 async def stt(file: UploadFile = File(...)):
+    """
+    Accepts an uploaded audio file (wav, mp3, m4a) and returns the transcribed text.
+    """
+    # Validate MIME type
+    if file.content_type not in ALLOWED_AUDIO_TYPES:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Unsupported audio format: {file.content_type}. Supported: WAV, MP3, M4A"
+        )
+
     try:
-        audio_bytes = await file.read()
-        text = await speech_to_text(audio_bytes)
+        audio_bytes = await file.read()  # Read uploaded file
+        text = await speech_to_text(audio_bytes)  # Call your Gemini STT
     except Exception as e:
         raise HTTPException(status_code=500, detail=str(e))
-
+    
     return {"text": text}
 
 
+
 # ------------------------
 # Voice Chatbot: User sends voice → TTS reply
 # ------------------------