Update app.py

app.py

@@ -1,46 +1,35 @@
 import gradio as gr
-import speech_recognition as sr
-from pydub import AudioSegment
-from io import BytesIO
-import tempfile
+import requests
 
-def transcribe_audio(audio_input):
-    recognizer = sr.Recognizer()
-    
-    if isinstance(audio_input, tuple) and len(audio_input) == 2:
-        audio_data_bytes = audio_input[1]
-    else:
-        raise ValueError("Expected audio_input to be a tuple with audio data bytes.")
-    
-    # Load audio as raw data
-    try:
-        audio_segment = AudioSegment.from_file(BytesIO(audio_data_bytes), format="mp3")
-    except Exception as e:
-        return f"Error loading audio file: {e}"
+# Function to send audio to Groq API and get transcription
+def transcribe(audio):
+    # Load audio data
+    audio_data = audio.read()
+
+    # Replace these placeholders with your actual Groq API endpoint and headers
+    groq_api_endpoint = "https://api.groq.com/transcribe"  # Example endpoint
+    headers = {
+        "Authorization": "Bearer YOUR_GROQ_API_KEY",
+        "Content-Type": "audio/wav",
+    }
 
-    # Save as WAV to a temporary file
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as wav_file:
-        audio_segment.export(wav_file.name, format="wav")
-        wav_file_path = wav_file.name
-    
-    # Transcribe the audio
-    try:
-        with sr.AudioFile(wav_file_path) as source:
-            audio_data = recognizer.record(source)
-            text = recognizer.recognize_google(audio_data)
-            return text
-    except sr.UnknownValueError:
-        return "Google Speech Recognition could not understand audio"
-    except sr.RequestError as e:
-        return f"Could not request results from Google Speech Recognition service; {e}"
+    # Send audio to Groq API
+    response = requests.post(groq_api_endpoint, headers=headers, data=audio_data)
+
+    # Parse response
+    if response.status_code == 200:
+        result = response.json()
+        return result.get("transcription", "No transcription available.")
+    else:
+        return f"Error: {response.status_code}, {response.text}"
 
-# Gradio Interface
+# Gradio interface
 iface = gr.Interface(
-    fn=transcribe_audio,
-    inputs="audio",
+    fn=transcribe,
+    inputs=gr.Audio(source="microphone", type="file"),
     outputs="text",
     title="Voice to Text Converter",
-    description="Upload an audio file and get the transcribed text."
+    description="Record your voice, and it will be transcribed into text using Groq API."
 )
 
 iface.launch()