patient_voice.py

import logging
from groq import Groq
import os
from dotenv import load_dotenv

# Load environment variables
load_dotenv()
GROQ_API_KEY = os.getenv("GROQ_API_KEY")
stt_model = "whisper-large-v3"

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

def transcribe_audio(file_path):
    """
    Transcribe audio to text using Groq Whisper.
    :param file_path: Path to the audio file.
    :return: Transcribed text.
    """
    try:
        with open(file_path, "rb") as audio_file:
            audio_data = audio_file.read()
            logging.info("Transcribing audio...")
            groq = Groq(api_key=GROQ_API_KEY)
            response = groq.audio.transcriptions.create(
                model=stt_model,
                file=audio_data,
                language="en",
                response_format="text"
            )
            logging.info("Audio transcription complete.")
            return response
    except Exception as e:
        logging.error(f"Error transcribing audio: {e}")
        return "Transcription failed. Check logs."