File size: 1,893 Bytes
be2b2cb |
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 72 73 74 75 |
from pathlib import Path
import streamlit as st
from audiorecorder import audiorecorder
from openai import OpenAI
open_ai = OpenAI(
api_key="sk-dW5stjNmgnwJb00p-Hk-oQCwGhHPNMoT9Nrx4yQvH4T3BlbkFJgoCDc7RdDufCuXRQNCpcq_m4oUswu217zkojwaxw4A")
st.set_page_config(
layout="centered",
page_icon="🤖",
page_title="Voice Chat"
)
st.title("Voice Chat")
if 'chat' not in st.session_state:
st.session_state.chat = []
def recordAudio():
audio = audiorecorder("Click to record", "Click to stop recording")
if len(audio) > 0:
audio.export("audio.wav", format="wav")
userPrompt = speechToText()
st.text(userPrompt)
st.session_state.chat.append({
'role': 'user',
'content': userPrompt
})
answer = getAnswer(userPrompt)
st.session_state.chat.append({
'role': 'assistant',
'content': answer
})
textToSpeech(answer)
st.audio("reply.wav", autoplay=True)
def speechToText():
audio_file = open("audio.wav", "rb")
transcription = open_ai.audio.transcriptions.create(
model="whisper-1",
file=audio_file
)
return transcription.text
def textToSpeech(text):
speech_file_path = Path(__file__).parent / "reply.wav"
response = open_ai.audio.speech.create(
model="tts-1",
voice="alloy",
input=text
)
response.stream_to_file(speech_file_path)
def getAnswer(question):
response = open_ai.chat.completions.create(
model="gpt-4o-mini",
messages=[
{"role": "system", "content": "You are a helpful assistant who can uderstand native urdu andwho provide very very short response in urdu"},
*st.session_state.chat,
{"role": "user", "content": question}
]
)
return response.choices[0].message.content
recordAudio() |