app.py

import gradio as gr
import openai
import os

openai.api_key = os.environ['OPENAI_API_KEY']


title = "Asistente en Transformación Digital" 

messages = [
    {"role": "system", "content": "Eres un asistente o consultor en temas de transformación digital. Limita tu respuesta a máximo 100 palabras"}
]


def transcribe(audio):
    global messages

    audio_filename_with_extension = audio + '.wav'
    os.rename(audio, audio_filename_with_extension)
    audio_file = open(audio_filename_with_extension, "rb")

    transcript = openai.Audio.transcribe("whisper-1", audio_file)

    messages.append({"role": "user", "content": transcript["text"]})

    response = openai.ChatCompletion.create(model="gpt-3.5-turbo",messages=messages)
    
    system_message = response["choices"][0]["message"]
    messages.append(system_message)

    chat_transcript = ""
    for message in messages:
        if message['role'] != "system":
            chat_transcript += message['role'] + ": " + message['content'] + "\n\n"

    return chat_transcript


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