diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..16d5987
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,37 @@
+/data
+/logs
+
+# Python
+__pycache__/
+*.py[cod]
+
+# Virtual environment
+venv/
+env/
+*.egg-info/
+dist/
+
+# IDE files
+.idea/
+.vscode/
+
+# Compiled files
+*.pyc
+*.pyo
+*.pyd
+
+# Temporary files
+*.bak
+*.swp
+*~
+
+# Logs
+*.log
+
+# User-specific files
+*.suo
+*.user
+*.sln.docstates
+
+# macOS
+.DS_Store
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..f475555
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,7 @@
+numpy==1.24.3
+scipy==1.11.2
+scikit-learn==1.3.0
+librosa==0.10.1
+tensorflow==2.13.0
+pyaudio==0.2.13
+matplotlib==3.7.0
\ No newline at end of file
diff --git a/src/__init__.py b/src/__init__.py
new file mode 100644
index 0000000..b2027cb
--- /dev/null
+++ b/src/__init__.py
@@ -0,0 +1,10 @@
+# __init__.py
+
+VERSION = "1.0.0"
+
+from . import capture_audio
+from . import process_audio
+from . import feature_extraction
+from . import machine_learning
+
+
diff --git a/src/capture_audio.py b/src/capture_audio.py
new file mode 100644
index 0000000..b5f55e0
--- /dev/null
+++ b/src/capture_audio.py
@@ -0,0 +1,51 @@
+# capture audio file from microphone
+import pyaudio
+import wave
+import time
+import sys
+
+from logging_config import logger
+
+# duration in seconds
+def capture_audio_to_file(output_file, duration=5, sample_rate=44100, channels=1):
+    audio = pyaudio.PyAudio()
+
+    try:
+        stream = audio.open(format=pyaudio.paInt16,
+                            channels=channels,
+                            rate=sample_rate,
+                            input=True,
+                            frames_per_buffer=1024)
+
+        print(f"Recording audio for {duration} seconds...")
+
+        frames = []
+        for _ in range(0, int(sample_rate / 1024 * duration)):
+            data = stream.read(1024)
+            frames.append(data)
+
+        print("Recording finished.")
+
+        stream.stop_stream()
+        stream.close()
+        audio.terminate()
+
+        # write to output wav file
+        with wave.open(output_file, 'wb') as wf:
+            wf.setnchannels(channels)
+            wf.setsampwidth(audio.get_sample_size(pyaudio.paInt16))
+            wf.setframerate(sample_rate)
+            wf.writeframes(b''.join(frames))
+
+    except Exception as e:
+        print(f"Error: {str(e)}")
+        logger.error(f"Error: {str(e)}")
+        return False
+
+    return True
+
+# test
+if __name__ == "__main__":
+    timestr = time.strftime("%Y%m%d_%H%M")
+    out_filename = f"../data/audio_samples/recorded_audio_{timestr}.wav"
+    capture_audio_to_file(out_filename, duration=5)
diff --git a/src/feature_extraction.py b/src/feature_extraction.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/logging_config.py b/src/logging_config.py
new file mode 100644
index 0000000..4ae6db5
--- /dev/null
+++ b/src/logging_config.py
@@ -0,0 +1,9 @@
+import logging
+
+logging.basicConfig(
+    filename='./logs/error.log',
+    level=logging.ERROR,
+    format='%(asctime)s - %(levelname)s - %(message)s'
+)
+
+logger = logging.getLogger(__name__)
diff --git a/src/machine_learning.py b/src/machine_learning.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/main.py b/src/main.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/process_audio.py b/src/process_audio.py
new file mode 100644
index 0000000..3ca08c5
--- /dev/null
+++ b/src/process_audio.py
@@ -0,0 +1,36 @@
+import librosa
+import librosa.display
+import matplotlib.pyplot as plt
+from logging_config import logger
+
+
+def process_audio_file(audio_file):
+    try:
+        # Load the audio file
+        y, sr = librosa.load(audio_file)
+
+        # Extract audio features (e.g., MFCCs)
+        mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=40)
+
+        # Display the audio waveform and MFCCs
+        plt.figure(figsize=(10, 6))
+        plt.subplot(2, 1, 1)
+        librosa.display.waveshow(y, sr=sr)
+        plt.title('Audio Waveform')
+
+        plt.subplot(2, 1, 2)
+        librosa.display.specshow(mfccs, x_axis='time')
+        plt.colorbar(format='%+2.0f dB')
+        plt.title('MFCCs')
+
+        plt.tight_layout()
+        plt.show()
+
+    except Exception as e:
+        print(f"Error: {str(e)}")
+        logger.error(f"Error: {str(e)}")
+
+
+if __name__ == "__main__":
+    recorded_audio_file = "../data/audio_samples/recorded_audio_20230911_1655.wav"
+    process_audio_file(recorded_audio_file)