Update app.py

app.py

@@ -1,49 +1,42 @@
 import openai
 import gradio as gr
+from dotenv import load_dotenv
 import os
 
-# Set up your OpenAI API key from environment variables
-openai.api_key = os.getenv('API_KEY')
+# Load environment variables from .env file
+load_dotenv()
 
-def transcribe_audio(file_path):
-    if file_path is None:
-        return "Error: No file path provided."
+# Set up OpenAI API key
+openai.api_key = os.getenv("OPENAI_API_KEY")
 
-    # Debugging: Print the file path
-    print(f"Received file path: {file_path}")
-
-    # Open the wav file
+def speech_to_text(audio):
+    # Check if the audio input is received correctly
+    if audio is None:
+        return "No audio file uploaded."
+    
     try:
-        audio_file = open(file_path, 'rb')
-        response = openai.audio.transcriptions.create(
-            model="whisper-1",  # specify the appropriate model for transcription
-            file=audio_file,
-            language='ta'  # specify 'ta' for Tamil language
-        )
-        audio_file.close()
+        # Open the audio file
+        with open(audio, "rb") as audio_file:
+            # Transcribe the audio to text using OpenAI's Whisper API
+            response = openai.Audio.transcriptions.create(
+                file=audio_file,
+                model="whisper-1",  # Use the appropriate model for transcription
+                language="ta"  # Specify the language as Tamil
+            )
+            text = response['text']
+            return text
     except Exception as e:
-        return f"Error during transcription: {e}"
-
-    # Extract the transcription text
-    transcription_text = response['text']
-    return transcription_text
-
-def transcribe_and_display(audio_path):
-    # Debugging: Print the audio path
-    print(f"Received audio path: {audio_path}")
-
-    # Transcribe the audio file
-    transcription = transcribe_audio(audio_path)
-    return transcription
+        return f"Error during transcription: {str(e)}"
 
-# Gradio interface
-iface = gr.Interface(
-    fn=transcribe_and_display,
-    inputs=gr.Audio(type="filepath"),
+# Set up the Gradio interface
+interface = gr.Interface(
+    fn=speech_to_text,
+    inputs=gr.Audio(source="upload", type="filepath"),
     outputs="text",
-    title="Speech to Text",
-    description="Upload a WAV file to transcribe speech to Tamil text."
+    title="Speech to Text Transcription",
+    description="Transcribe speech to Tamil text using OpenAI's API."
 )
 
 # Launch the interface
-iface.launch()
+if __name__ == "__main__":
+    interface.launch()