app.py

import os 


os.system("apt install libasound2-dev portaudio19-dev libportaudio2 libportaudiocpp0 ffmpeg")
import sounddevice as sd
import speech_recognition as sr
def takeCommand(audio):
    r = sr.Recognizer()
    with sr.AudioFile(
        audio
    ) as source:  # Replace "audio.wav" with the path to your .wav file
        # print("Listening...")
        audio_data = r.record(source)

    try:
        # print("Recognizing...")
        query = r.recognize_google(audio_data, language="en-in")
        print(f"User said: {query}")
        return query
    except sr.UnknownValueError:
        print("Unable to recognize speech")
    except sr.RequestError as e:
        print(f"Error occurred: {e}")

    return "Some error occurred. Sorry from Jarvis"



k=gr.Interface(fn=takeCommand, inputs=gr.Audio(source="microphone", type="filepath"), outputs="text")
k.launch()