m4a audio file to text

main.py

import speech_recognition as sr
import sys
from pydub import AudioSegment

if __name__ == "__main__":
	args = sys.argv
	if len(args) < 3:
		print("Input filename, language(ex. ko-KR)")
		exit(0);

	speech = AudioSegment.from_file(args[1], "m4a")
	speech.export("output.wav", format="wav")
	recognizer = sr.Recognizer()
	recognizer.energy_threshold = 300
	audiofile = sr.AudioFile("output.wav")

	with audiofile as source:
		audio = recognizer.record(source)
	
	print(recognizer.recognize_google(audio_data=audio, language=args[2]))