app.py

import gradio as gr
import openai
from elevenlabslib import *
from pydub import AudioSegment
from pydub.playback import play
import io
import winsound

openai.api_key = "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"
api_key = "929b67c6e533e94018a438d70c960b60"
from elevenlabslib import ElevenLabsUser
user = ElevenLabsUser(api_key)

messages = ["Respond with voice"]

def transcribe(audio):
    global messages

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

    messages.append(f"\nUser: {transcript['text']}")

    response = openai.Completion.create(
        engine="text-davinci-003",
        prompt=messages[-1],
        max_tokens=60,
        n=1,
        stop=None,
        temperature=0.5,
    )

    system_message = response["choices"][0]["text"]
    messages.append(f"{system_message}")

    voice = user.get_voices_by_name("Bella")[0]
    audio = voice.generate_audio_bytes(system_message)

    audio = AudioSegment.from_file(io.BytesIO(audio), format="mp3")
    audio.export("output.wav", format="wav")

    winsound.PlaySound("output.wav", winsound.SND_FILENAME)

    chat_transcript = "\n".join(messages)
    return chat_transcript

iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(source="microphone", type="filepath"),
    outputs="text",
    title="Voice Assistant",
)

iface.launch()