Detect sounds to Keypress

detectSound.py

import scipy.io.wavfile as wavfile
import scipy.signal as signal

# Load the audio file
fs, data = wavfile.read('sound_file.wav')

# Calculate the spectrogram
f, t, Sxx = signal.spectrogram(data, fs)

# Find the indices of the frequency bins that correspond to the minimum and maximum frequencies
min_idx = 0
max_idx = len(f) - 1
for i in range(len(f)):
    if f[i] >= min_freq:
        min_idx = i
        break
for i in range(len(f)-1, -1, -1):
    if f[i] <= max_freq:
        max_idx = i
        break

# Calculate the minimum and maximum frequencies
min_freq = f[min_idx]
max_freq = f[max_idx]

print('Minimum frequency:', min_freq)
print('Maximum frequency:', max_freq)

DetectSounds.py

import sounddevice as sd
import numpy as np
import librosa
import pynput.keyboard as keyboard

# Set the minimum and maximum frequencies for the "ahh" sound
min_freq = 500
max_freq = 2000

# Set the minimum and maximum frequencies for the "ssss" sound
min_freq_s = 1000
max_freq_s = 4000

# Define the function to detect the "ahh" sound
def detect_ahh(indata, frames, time, status):
    # Compute the mel spectrogram
    S = librosa.feature.melspectrogram(y=indata[:, 0], sr=44100, n_mels=64, fmin=min_freq, fmax=max_freq)
    # Flatten the spectrogram
    S = S.flatten()
    # Compute the RMS (root mean square) energy of the sound
    rms = np.sqrt(np.mean(np.square(indata[:, 0])))
    # Check if the energy of the sound is above a certain threshold
    if rms > 0.01:
        # Compute the mean of the mel spectrogram
        S_mean = np.mean(S)
        # Check if the mean of the mel spectrogram is above a certain threshold
        if S_mean > 50:
            # Press the F1 key
            keyboard.Controller().press(keyboard.Key.f1)

# Define the function to detect the "ssss" sound
def detect_ssss(indata, frames, time, status):
    # Compute the mel spectrogram
    S = librosa.feature.melspectrogram(y=indata[:, 0], sr=44100, n_mels=64, fmin=min_freq_s, fmax=max_freq_s)
    # Flatten the spectrogram
    S = S.flatten()
    # Compute the RMS (root mean square) energy of the sound
    rms = np.sqrt(np.mean(np.square(indata[:, 0])))
    # Check if the energy of the sound is above a certain threshold
    if rms > 0.01:
        # Compute the mean of the mel spectrogram
        S_mean = np.mean(S)
        # Check if the mean of the mel spectrogram is above a certain threshold
        if S_mean > 50:
            # Press the F2 key
            keyboard.Controller().press(keyboard.Key.f2)

# Start the microphone recording
with sd.InputStream(callback=detect_ahh, blocksize=2048):
    with sd.InputStream(callback=detect_ssss, blocksize=2048):
        sd.sleep(10000)

requirements.txt

librosa==0.8.1
numpy==1.21.5
pynput==1.7.3
pyaudio==0.2.11