SPEECH RECOGNITION USING PYTHON

Getting input from microphone

# Getting input from microphone
import speech_recognition as sr

# Initializing microphone to listen
with sr.Microphone() as source:
    print("listening....")
    # Storing the audio source in a variable
    audio = sr.Recognizer().listen(source)

# Converting audio into string
data = sr.Recognizer().recognize_google(audio, language="en-in")
print(data)

Getting input from existing audio file

# Getting input from existing audio file
import speech_recognition as sr

# using exiting audio file as a source
with sr.WavFile("filename.mp3") as source:
    # Storing the audio source in a variable
    audio = sr.Recognizer().listen(source)

# converting audio into string
audio_content = sr.Recognizer().recognize_google(audio, language="en-in")
print(audio_content)

Listening to microphone in background

# listening to microphone in background
import speech_recognition as sr

# Infinite loop
while True:
    try:
        # Initializing microphone to listen
        with sr.Microphone() as source:
            print("Listening...")

            # Storing the audio source in a variable
            audio = sr.Recognizer().listen(source)

        # Converting audio into string
        query = sr.Recognizer().recognize_google(audio, language="en-in")
        print(query)

        # Loop termination
        if query == "exit":
            exit()

    except Exception as e:
        print(e)

Refer pypi.org website

Also Refer : Text-to-Speech using python