toTranscribe.py

import pyaudio
import wave
from pynput import keyboard
import speech_recognition as sr

FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 44100
CHUNK = 1024
RECORD_SECONDS = 10
WAVE_OUTPUT_FILENAME = "2.wav"

frames = []

#def transcribe(wav):
    

def on_press(key):
    #if key == keyboard.Key.esc:
    #    recording = False
    #    return False
    if key == keyboard.KeyCode.from_char('a'):
        print("Recording audio...")
        # Start recording
        global stream, audio
        audio = pyaudio.PyAudio()
        stream = audio.open(format=FORMAT, channels=CHANNELS,
                            rate=RATE, input=True,
                            frames_per_buffer=CHUNK)
        for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
            data = stream.read(CHUNK)
            frames.append(data)

        # Stop recording
        stream.stop_stream()
        stream.close()
        audio.terminate()
        print("Finished recording audio.")
        audio_data = sr.AudioData(b''.join(frames), RATE, 2)
        print(audio_data)
        #r = sr.Recognizer()
        #text = r.recognize_google(audio_data)
        #print(text)
        
def on_release(key):
    if key == keyboard.Key.esc:
        return False

# Start the listener
with keyboard.Listener(on_press=on_press, on_release=on_release) as listener:
    listener.join()