voice_of_the_patient.py

import logging
import speech_recognition as sr
from pydub import AudioSegment
from io import BytesIO

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


def record_audio(file_path , duration=20 , phrase_time_limit= None):
    recognizer = sr.Recognizer()

    try:
        with sr.Microphone() as source:
            logging.info("Adjusting for ambient noise...")
            recognizer.adjust_for_ambient_noise(source)
            logging.info("Recording audio...")

            # Record the audio
            audio_data = recognizer.listen(source , timeout=duration , phrase_time_limit=phrase_time_limit)
            logging.info("Recording complete.")

            # Convert the recorded audio to an MP3 file
            audio_waves = audio_data.get_wav_data()
            audio_segments = AudioSegment.from_wav(BytesIO(audio_waves))
            audio_segments.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 while recording audio: {e}")

audio_filePath = "patient_voice.mp3"
record_audio(file_path= audio_filePath)

import os
from groq import Groq
from dotenv import load_dotenv

load_dotenv()


GROQ_API_KEY = os.getenv("GROQ_API_KEY")
sst_model = "whisper-large-v3"

def transcription_with_groq(audio_filePath , sst_model , GROQ_API_KEY):
    try:
        groq_client = Groq(api_key = GROQ_API_KEY)
        audio_file = open(audio_filePath , "rb")
        transcription = groq_client.audio.transcriptions.create(
            model = sst_model,
            file = audio_file,
            language = "en"
        )
        logging.info("Transcription complete.")
        print(transcription.text)
        return transcription.text
    except Exception as e:
        logging.error(f"An error occurred during transcription: {e}")

transcription_with_groq(audio_filePath=audio_filePath , sst_model=sst_model,GROQ_API_KEY=GROQ_API_KEY)