Update app.py

app.py

@@ -7,27 +7,38 @@ def transcribe(audio_path):
     with open(audio_path, "rb") as audio_file:
         audio_data = audio_file.read()
 
-    # Replace these placeholders with your actual Groq API endpoint and headers
-    groq_api_endpoint = "https://api.groq.com/transcribe"  # Example endpoint
+    # Groq API endpoint for audio transcription
+    groq_api_endpoint = "https://api.groq.com/openai/v1/audio/transcriptions"
+
+    # Replace 'YOUR_GROQ_API_KEY' with your actual Groq API key
     headers = {
-        "Authorization": "Bearer YOUR_GROQ_API_KEY",
-        "Content-Type": "audio/wav",
+        "Authorization": "Bearer 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",
+    }
+
+    # Prepare the files and data for the request
+    files = {
+        'file': ('audio.wav', audio_data, 'audio/wav'),
+    }
+    data = {
+        'model': 'whisper-large-v3-turbo',  # Specify the model to use
+        'response_format': 'json',          # Desired response format
+        'language': 'en',                   # Language of the audio
     }
 
     # Send audio to Groq API
-    response = requests.post(groq_api_endpoint, headers=headers, data=audio_data)
+    response = requests.post(groq_api_endpoint, headers=headers, files=files, data=data)
 
     # Parse response
     if response.status_code == 200:
         result = response.json()
-        return result.get("transcription", "No transcription available.")
+        return result.get("text", "No transcription available.")
     else:
         return f"Error: {response.status_code}, {response.text}"
 
 # Gradio interface
 iface = gr.Interface(
     fn=transcribe,
-    inputs=gr.Audio(type="filepath"),
+    inputs=gr.Audio(source="microphone", type="filepath"),
     outputs="text",
     title="Voice to Text Converter",
     description="Record your voice, and it will be transcribed into text using Groq API."