Update app.py

app.py

@@ -7,9 +7,10 @@ import os
 from gtts import gTTS
 import speech_recognition as sr
 from groq import Groq
+import tempfile
 
 # Set up Groq API
-groq_api_key = "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"
+groq_api_key = os.getenv("GROQ_API_KEY")
 client = Groq(api_key=groq_api_key)
 
 def process_text(text):
@@ -36,16 +37,18 @@ def text_to_speech(text, lang='ur'):
 def audio_to_text(audio_file):
     # Convert audio to text
     recognizer = sr.Recognizer()
-    audio = sr.AudioFile(audio_file)
-    with audio as source:
-        audio_data = recognizer.record(source)
-        try:
-            text = recognizer.recognize_google(audio_data, language='ur')
-            return text
-        except sr.UnknownValueError:
-            return "Could not understand audio"
-        except sr.RequestError as e:
-            return f"Could not request results; {e}"
+    with tempfile.NamedTemporaryFile(delete=False) as temp_file:
+        temp_file.write(audio_file.read())
+        temp_file.seek(0)
+        with sr.AudioFile(temp_file.name) as source:
+            audio_data = recognizer.record(source)
+            try:
+                text = recognizer.recognize_google(audio_data, language='ur')
+                return text
+            except sr.UnknownValueError:
+                return "Could not understand audio"
+            except sr.RequestError as e:
+                return f"Could not request results; {e}"
 
 # Streamlit UI
 st.title("Urdu Voice Assistant")
@@ -80,8 +83,15 @@ elif mode == "Upload Voice File":
     uploaded_file = st.file_uploader("Upload an audio file", type=["wav", "mp3"])
     if uploaded_file:
         st.write("Processing...")
-        # Convert the uploaded file to text
-        text = audio_to_text(uploaded_file)
+        # Convert uploaded file to WAV format if needed
+        if uploaded_file.type == "audio/mpeg":
+            audio = AudioSegment.from_mp3(uploaded_file)
+            with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_file:
+                audio.export(temp_file.name, format="wav")
+                with open(temp_file.name, "rb") as temp_file_content:
+                    text = audio_to_text(temp_file_content)
+        else:
+            text = audio_to_text(uploaded_file)
         st.write(f"Transcribed Text: {text}")
 
         # Get response from Groq
@@ -91,4 +101,3 @@ elif mode == "Upload Voice File":
         # Convert response to audio
         audio_file = text_to_speech(response_text)
         st.audio(audio_file, format='audio/mp3')
-