The current top answer is a bit outdated and only works for python 2. Here is a version updated for python 3. It wraps the functions into classes and packages everything into one simple easy-to-use version. Note that there is one key difference between the top answer and my script:
The script at the top records for one file and then stops, while my script keeps recording whenever noise is detected and dumps the recordings into a directory as it goes.
The main idea for both scripts are pretty similar:
Step 1: ‘Listen’ until rms becomes greater than the threshold
Step 2: Start recording, set a timer for when to stop recording, == TIMEOUT_LENGTH
Step 3: If the rms breaks threshold again before the timer times out reset the timer
Step 4: Now that the timer is expired, write the recording to a directory and go back to step 1
import pyaudio
import math
import struct
import wave
import time
import os
Threshold = 10
SHORT_NORMALIZE = (1.0/32768.0)
chunk = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
swidth = 2
TIMEOUT_LENGTH = 5
f_name_directory = r'C:\Users\Jason\PyCharmProjects\AutoRecorder\records'
class Recorder:
@staticmethod
def rms(frame):
count = len(frame) / swidth
format = "%dh" % (count)
shorts = struct.unpack(format, frame)
sum_squares = 0.0
for sample in shorts:
n = sample * SHORT_NORMALIZE
sum_squares += n * n
rms = math.pow(sum_squares / count, 0.5)
return rms * 1000
def __init__(self):
self.p = pyaudio.PyAudio()
self.stream = self.p.open(format=FORMAT,
channels=CHANNELS,
rate=RATE,
input=True,
output=True,
frames_per_buffer=chunk)
def record(self):
print('Noise detected, recording beginning')
rec = []
current = time.time()
end = time.time() + TIMEOUT_LENGTH
while current <= end:
data = self.stream.read(chunk)
if self.rms(data) >= Threshold: end = time.time() + TIMEOUT_LENGTH
current = time.time()
rec.append(data)
self.write(b''.join(rec))
def write(self, recording):
n_files = len(os.listdir(f_name_directory))
filename = os.path.join(f_name_directory, '{}.wav'.format(n_files))
wf = wave.open(filename, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(self.p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(recording)
wf.close()
print('Written to file: {}'.format(filename))
print('Returning to listening')
def listen(self):
print('Listening beginning')
while True:
input = self.stream.read(chunk)
rms_val = self.rms(input)
if rms_val > Threshold:
self.record()
a = Recorder()
a.listen()