ashank-pitch 0.1.0

A CLI tool for real-time pitch detection while singing

Sing Detector 🎤

A real-time pitch detection CLI tool for singers. Analyze your voice and see what note you're singing in real-time!

Features

• 🎵 Real-time pitch detection while you sing
• 🎯 Shows musical note names (C, D, E, etc.) with octave
• 📊 Displays frequency in Hz
• 🎶 Shows how close you are to perfect pitch (in cents)
• ⚡ Two detection algorithms: Autocorrelation and FFT
• 🖥️ Simple command-line interface

Installation

From Source

1. Clone or download this repository
2. Install the package:

pip install -e .

System Requirements

• Python 3.7 or higher
• A working microphone
• Audio drivers compatible with PyAudio

Dependencies

The package will automatically install:

• numpy - For numerical computations
• scipy - For signal processing
• pyaudio - For audio input capture

Usage

Basic Usage

Simply run:

sing

This will start the real-time pitch detector using your default microphone.

Advanced Options

# Use FFT method instead of autocorrelation
sing --method fft

# Change sample rate (default: 44100 Hz)
sing --rate 22050

# Change update rate (default: 20 Hz)
sing --update-rate 30

# Change audio frame size (default: 4096 samples)
sing --frame-size 2048

# Show help
sing --help

Example Output

🎤 Sing Detector - Real-time Pitch Detection
==================================================
Start singing! Press Ctrl+C to stop.

🎵 A4 (440.0 Hz) - in tune
🎵 C5 (523.3 Hz) - +12 cents
🔇 No clear pitch detected...

How It Works

The tool captures audio from your microphone in real-time and analyzes it using digital signal processing techniques:

1. Audio Capture: Uses PyAudio to capture audio from your default microphone
2. Windowing: Applies a Hanning window to reduce spectral leakage
3. Pitch Detection: Uses either:
   • Autocorrelation: Finds repeating patterns in the audio signal
   • FFT: Analyzes frequency spectrum to find the fundamental frequency
4. Note Conversion: Converts frequency to musical note names using equal temperament tuning
5. Cents Calculation: Shows how close you are to perfect pitch (±50 cents = ±half semitone)

Troubleshooting

"No audio devices found" Error

This usually means PyAudio can't access your microphone. Try:

1. macOS: Grant microphone permissions to your terminal application
2. Linux: Install ALSA development headers: sudo apt-get install libasound2-dev
3. Windows: Make sure your microphone is set as the default recording device

PyAudio Installation Issues

If PyAudio fails to install:

macOS:

brew install portaudio
pip install pyaudio

Linux (Ubuntu/Debian):

sudo apt-get install portaudio19-dev python3-pyaudio
pip install pyaudio

Windows:

pip install pipwin
pipwin install pyaudio

Poor Pitch Detection

If the tool isn't detecting your voice well:

1. Try singing louder and clearer
2. Reduce background noise
3. Try the alternative detection method: sing --method fft
4. Experiment with different frame sizes: sing --frame-size 2048

Development

Running from Source

python -m sing_detector.main

Testing

You can test the package installation:

# Install in development mode
pip install -e .

# Test the command
sing --help

Contributing

Feel free to open issues or submit pull requests!

License

MIT License - feel free to use and modify as needed.

---

Happy singing! 🎵