edits to transcribe agent

agent-mAId/main.py

@@ -22,18 +22,20 @@
 # if __name__ == "__main__":
 #     main()
 
-
+import os
+from groq import Groq
 import pyaudio
 import wave
 import pyautogui
-import requests
 import keyboard
 
 # Constants
-API_URL = "https://api.openai.com/v1/whisper"
-API_KEY = "your_openai_api_key"
+API_KEY = "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"  # Make sure to use your actual API key
 BUTTON = 'ctrl'  # The button to listen for
 
+# Initialize the Groq client
+client = Groq(api_key=API_KEY)
+
 def record_audio(filename):
     # Setup audio recording
     audio = pyaudio.PyAudio()
@@ -42,8 +44,8 @@ def record_audio(filename):
     frames = []
     print("Recording...")
 
-    # Record while button is pressed
-    while keyboard.is_pressed(BUTTON):
+    # Record while button or mouse is pressed
+    while keyboard.is_pressed(BUTTON) or mouse.is_pressed(button='left'):
         data = stream.read(1024)
         frames.append(data)
     
@@ -61,14 +63,17 @@ def record_audio(filename):
     wave_file.close()
 
 def transcribe_audio(filename):
-    # Transcribe audio using Whisper API
-    with open(filename, 'rb') as audio_file:
-        response = requests.post(
-            API_URL,
-            headers={"Authorization": f"Bearer {API_KEY}"},
-            files={"file": audio_file}
+    # Open the audio file
+    with open(filename, "rb") as file:
+        # Create a transcription of the audio file
+        transcription = client.audio.transcriptions.create(
+            file=(filename, file.read()),  # Required audio file
+            model="distil-whisper-large-v3-en",  # Required model to use for transcription
+            prompt="Specify context or spelling",  # Optional
+            response_format="json",  # Optional
+            temperature=0.0  # Optional
         )
-    return response.json().get('text', '')
+    return transcription['text']
 
 def simulate_keypress(text):
     # Simulate keypress for each character in text