app.py

import os
import gradio as gr
import openai
from dotenv import load_dotenv
from langchain.llms import OpenAI

load_dotenv()

def process(filepath):
    audio = open(filepath,"rb")
    my_key = os.getenv("OPENAI_API_KEY")
    openai.api_key = my_key
    transcript = openai.Audio.transcribe("whisper-1", audio)
    
    llm = OpenAI(
        model="gpt-3.5-turbo",
        temperature=1, 
        openai_api_key=my_key
    )
    trans=[transcript["text"], llm(transcript["text"])]
    return trans

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