text_speech_utils.py

import speech_recognition as sr
from gtts import gTTS
import os
import wave

def record_audio(filename, sec=5, sr=44100):
    # Initialize recognizer class (for recognizing speech)
    recognizer = sr.Recognizer()

    # Set the microphone for recording
    with sr.Microphone() as source:
        print("Recording... Speak now!")
        recognizer.adjust_for_ambient_noise(source)  # Adjust for ambient noise
        audio = recognizer.listen(source, timeout=sec)
        
        # Save the audio to a file
        with open(filename, "wb") as f:
            f.write(audio.get_wav_data())

def transcribe_audio(filename):
    recognizer = sr.Recognizer()
    
    with sr.AudioFile(filename) as source:
        audio = recognizer.record(source)
    
    try:
        # Recognize speech using Google's speech recognition
        transcript = recognizer.recognize_google(audio)
        return {"text": transcript}
    except sr.UnknownValueError:
        return {"text": "Sorry, I could not understand the audio."}
    except sr.RequestError as e:
        return {"text": f"Request failed; {e}"}

def save_text_as_audio(text, audio_filename):
    tts = gTTS(text=text, lang='en', slow=False)  
    tts.save(audio_filename)

def play_audio(filename):
    # Play audio using the default system player (e.g., vlc, mplayer)
    os.system(f"start {filename}")  # For Windows; on Linux/macOS use `os.system(f"mpg321 {filename}")`