Spaces:
Sleeping
Sleeping
File size: 1,678 Bytes
034895f 4cdfeed 034895f 43a9c3d 034895f 4cdfeed 034895f 60d0165 034895f 37f7177 034895f fee5ff6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
#pip install openai
#pip install gradio
#pip install pyttsx3
#pip install pydantic
#pip install openai gradio pyttsx3 pydantic
#pip install python-dotenv
import gradio as gr
import openai
import pyttsx3
#import pydantic
from dotenv import load_dotenv
import os
load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")
#openai.api_key = ""
# Global variable to hold the chat history, initialise with system role
conversation = [
{"role": "system", "content": "You are an intelligent professor."}
]
# transcribe function to record the audio input
def transcribe(audio):
print(audio)
# Whisper API
audio_file = open(audio, "rb")
transcript = openai.Audio.transcribe("whisper-1", audio_file)
print(transcript)
# ChatGPT API
# append user's inut to conversation
conversation.append({"role": "user", "content": transcript["text"]})
response = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=conversation
)
print(response)
# system_message is the response from ChatGPT API
system_message = response["choices"][0]["message"]["content"]
# append ChatGPT response (assistant role) back to conversation
conversation.append({"role": "assistant", "content": system_message})
# Text to speech
engine = pyttsx3.init()
engine.setProperty("rate", 150)
engine.setProperty("voice", "english-us")
engine.save_to_file(system_message, "response.mp3")
engine.runAndWait()
return "response.mp3"
# Gradio output
bot = gr.Interface(fn=transcribe, inputs=gr.Audio(source="microphone", type="filepath"), outputs="audio")
bot.launch(share=False)
iface.share() |