audio_utils.py

import logging
import os
import platform
import subprocess
from io import BytesIO

import speech_recognition as sr
from gtts import gTTS
from pydub import AudioSegment
from groq import Groq

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

def record_audio(file_path, timeout=20, phrase_time_limit=None):
    """
    Simplified function to record audio from the microphone and save it as an MP3 file.
    """
    recognizer = sr.Recognizer()
    
    try:
        with sr.Microphone() as source:
            logging.info("Adjusting for ambient noise...")
            recognizer.adjust_for_ambient_noise(source, duration=1)
            logging.info("Start speaking now...")
            
            audio_data = recognizer.listen(source, timeout=timeout, phrase_time_limit=phrase_time_limit)
            logging.info("Recording complete.")
            
            wav_data = audio_data.get_wav_data()
            audio_segment = AudioSegment.from_wav(BytesIO(wav_data))
            audio_segment.export(file_path, format="mp3", bitrate="128k")
            
            logging.info(f"Audio saved to {file_path}")

    except Exception as e:
        logging.error(f"An error occurred: {e}")

def transcribe_with_groq(stt_model, audio_filepath, groq_api_key):
    """
    Transcribes an audio file using the Groq API.
    """
    client = Groq(api_key=groq_api_key)
    
    with open(audio_filepath, "rb") as audio_file:
        transcription = client.audio.transcriptions.create(
            model=stt_model,
            file=audio_file,
            language="en"
        )
    return transcription.text

def text_to_speech_with_gtts(input_text, output_filepath="gtts_output.mp3"):
    """
    Converts text to speech using gTTS and handles playback.
    """
    tts = gTTS(text=input_text, lang="en", slow=False)
    tts.save(output_filepath)

    os_name = platform.system()
    try:
        if os_name == "Darwin":  # macOS
            subprocess.run(['afplay', output_filepath])
        elif os_name == "Windows":  # Windows
            subprocess.run([
                'powershell',
                '-c',
                f'(New-Object Media.SoundPlayer "{output_filepath}").PlaySync();'
            ])
        elif os_name == "Linux":
            subprocess.run(['aplay', output_filepath])
        else:
            raise OSError("Unsupported OS for audio playback.")
    except Exception as e:
        print(f"[Audio Playback Error] {e}")

    return output_filepath