Made changes for cloudinary links downlaod

app.py

@@ -39,53 +39,118 @@ def health_check():
     return jsonify({"status": "success", "message": "API is running successfully!"}), 200
 
 
-@app.route('/process-audio', methods=['POST'])
-def process_audio():
-    # print("GOT THE PROCESS AUDIO REQUEST, ANIKET")
+# @app.route('/process-audio', methods=['POST'])
+# def process_audio():
+#     # print("GOT THE PROCESS AUDIO REQUEST, ANIKET")
     
-    if 'audio' not in request.files:
-        return jsonify({"error": "No audio file provided"}), 400
+#     if 'audio' not in request.files:
+#         return jsonify({"error": "No audio file provided"}), 400
 
-    audio_file = request.files['audio']
-    # print("AUDIO FILE NAME: ", audio_file)
+#     audio_file = request.files['audio']
+#     # print("AUDIO FILE NAME: ", audio_file)
 
-    temp_audio_path = None
-    try:
-        print("STARTING TRANSCRIPTION, ANIKET")
+#     temp_audio_path = None
+#     try:
+#         print("STARTING TRANSCRIPTION, ANIKET")
         
-        # Step 1: Save the audio file temporarily to a specific location
-        with tempfile.NamedTemporaryFile(delete=False, suffix='.wav') as temp_audio_file:
-            temp_audio_path = temp_audio_file.name  # Get the file path
-            temp_audio_file.write(audio_file.read())  # Write the uploaded audio to the temp file
+#         # Step 1: Save the audio file temporarily to a specific location
+#         with tempfile.NamedTemporaryFile(delete=False, suffix='.wav') as temp_audio_file:
+#             temp_audio_path = temp_audio_file.name  # Get the file path
+#             temp_audio_file.write(audio_file.read())  # Write the uploaded audio to the temp file
         
-        # print(f"Temporary audio file saved at: {temp_audio_path}")
+#         # print(f"Temporary audio file saved at: {temp_audio_path}")
         
-        # Step 2: Transcribe the uploaded audio file synchronously
-        transcription = transcribe_audio(temp_audio_path)
+#         # Step 2: Transcribe the uploaded audio file synchronously
+#         transcription = transcribe_audio(temp_audio_path)
+
+#         # print("BEFORE THE transcription FAILED ERROR, CHECKING IF I GOT THE TRANSCRIPTION", transcription)
+
+#         if not transcription:
+#             return jsonify({"error": "Audio transcription failed"}), 500
+
+#         # print("GOT THE transcription")
+
+#         # Step 3: Generate structured recipe information using Gemini API synchronously
+#         # print("Starting the GEMINI REQUEST TO STRUCTURE IT")
+#         structured_data = query_gemini_api(transcription)
+
+#         # print("GOT THE STRUCTURED DATA", structured_data)
+#         # Step 4: Return the structured data
+#         return jsonify(structured_data)
+
+#     except Exception as e:
+#         return jsonify({"error": str(e)}), 500
+
+#     finally:
+#         # Clean up the temporary WAV file
+#         if temp_audio_path and os.path.exists(temp_audio_path):
+#             os.remove(temp_audio_path)
+#             print(f"Temporary WAV file deleted: {temp_audio_path}")
+
+def download_video(url, temp_video_path):
+    """Download video from the given URL and save it to temp_video_path."""
+    response = requests.get(url, stream=True)
+    if response.status_code == 200:
+        with open(temp_video_path, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=1024):
+                f.write(chunk)
+        print(f"Video downloaded successfully to {temp_video_path}")
+    else:
+        raise Exception(f"Failed to download video, status code: {response.status_code}")
+
+def convert_to_wav(video_path, wav_path):
+    """Convert video file to WAV format using FFmpeg."""
+    try:
+        ffmpeg_command = [
+            "ffmpeg", "-i", video_path, "-q:a", "0", "-map", "a", wav_path
+        ]
+        subprocess.run(ffmpeg_command, check=True)
+        print(f"Video converted to WAV successfully: {wav_path}")
+    except subprocess.CalledProcessError as e:
+        raise Exception(f"FFmpeg conversion failed: {e}")
+
+@app.route('/process-audio', methods=['POST'])
+def process_audio():
+    if 'audioUrl' not in request.json:
+        return jsonify({"error": "No audio URL provided"}), 400
 
-        # print("BEFORE THE transcription FAILED ERROR, CHECKING IF I GOT THE TRANSCRIPTION", transcription)
+    audio_url = request.json['audioUrl']
+    temp_video_path = None
+    temp_wav_path = None
+
+    try:
+        # Step 1: Download the video file from the Cloudinary URL
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".mp4") as temp_video_file:
+            temp_video_path = temp_video_file.name
+            download_video(audio_url, temp_video_path)
+
+        # Step 2: Convert the downloaded video to WAV format
+        temp_wav_path = temp_video_path.replace(".mp4", ".wav")
+        convert_to_wav(temp_video_path, temp_wav_path)
+
+        # Step 3: Transcribe the audio file synchronously
+        transcription = transcribe_audio(temp_wav_path)
 
         if not transcription:
             return jsonify({"error": "Audio transcription failed"}), 500
 
-        # print("GOT THE transcription")
-
-        # Step 3: Generate structured recipe information using Gemini API synchronously
-        # print("Starting the GEMINI REQUEST TO STRUCTURE IT")
+        # Step 4: Generate structured recipe information using Gemini API synchronously
         structured_data = query_gemini_api(transcription)
 
-        # print("GOT THE STRUCTURED DATA", structured_data)
-        # Step 4: Return the structured data
         return jsonify(structured_data)
 
     except Exception as e:
         return jsonify({"error": str(e)}), 500
 
     finally:
-        # Clean up the temporary WAV file
-        if temp_audio_path and os.path.exists(temp_audio_path):
-            os.remove(temp_audio_path)
-            print(f"Temporary WAV file deleted: {temp_audio_path}")
+        # Clean up temporary files
+        if temp_video_path and os.path.exists(temp_video_path):
+            os.remove(temp_video_path)
+            print(f"Temporary video file deleted: {temp_video_path}")
+
+        if temp_wav_path and os.path.exists(temp_wav_path):
+            os.remove(temp_wav_path)
+            print(f"Temporary WAV file deleted: {temp_wav_path}")