audio_bot / app.py
nanostuff's picture
Update app.py
bb242b8
Raw History Blame Contribute Delete
7.16 kB
import gradio as gr
import openai
import os
from gtts import gTTS
# from langdetect import detect
# Initialize the OpenAI API with your key and organization ID
openai.api_key = os.getenv('OPEN_API_KEY')
# all_messages = [] # List to store all conversation messages
all_messages = [{"role": "system", "content": 'You are an AI chatbot. Respond to all input in 25 words or less'}]
# def initialize_session():
# return [{"role": "system", "content": 'You are an AI chatbot. Respond to all input in 25 words or less'}]
# all_messages = initialize_session()
open("output_audio.mp3", "wb").close()
def transcribe(audio, text):
global all_messages
language = 'en'
transcript = {}
# if audio:
# audio_filename_with_extension = audio + '.wav'
# os.rename(audio, audio_filename_with_extension)
# audio_file = open(audio_filename_with_extension, "rb")
# # Transcribe the audio file using the whisper-1 model
# transcript = openai.audio.transcriptions.create(model="whisper-1", file=audio_file)
# print("Transcription:", transcript)
# # user_input = transcript("text") if isinstance(transcript, dict) else ""
# # user_input = transcript.text if isinstance(transcript, dict) else ""
# user_input = transcript.get("text", "") if isinstance(transcript, dict) else ""
# user_input = transcript.text
# print("Transcription:", user_input)
# else :
# user_input = text
if audio:
audio_filename_with_extension = audio + '.wav'
os.rename(audio, audio_filename_with_extension)
audio_file = open(audio_filename_with_extension, "rb")
# Transcribe the audio file using the whisper-1 model
transcript = openai.audio.transcriptions.create(model="whisper-1", file=audio_file)
print("Transcription:", transcript)
# user_input = transcript("text") if isinstance(transcript, dict) else ""
# user_input = transcript.text if isinstance(transcript, dict) else ""
user_input = transcript.get("text", "") if isinstance(transcript, dict) else ""
user_input = transcript.text
print("Transcription:", user_input)
else:
user_input = text
# if not all_messages or (len(all_messages) == 1 and all_messages[0]["role"] == "system"):
# all_messages = initialize_session()
conversation_tokens = sum(len(message['content'].split()) for message in all_messages)
# Limit the conversation tokens to the model's maximum limit (4096 - a safety margin)
max_conversation_tokens = 4000
while conversation_tokens > max_conversation_tokens:
oldest_message_tokens = len(all_messages[0]['content'].split())
if conversation_tokens - oldest_message_tokens > max_conversation_tokens:
all_messages.pop(0)
conversation_tokens -= oldest_message_tokens
else:
break
# all_messages.append = [{"role": "system", "content": 'You are an AI chatbot. Respond to all input in 25 words or less'}]
all_messages.append({"role": "user", "content": user_input})
# Generate a chat response using the gpt-3.5-turbo model
response = openai.chat.completions.create(model="gpt-3.5-turbo", messages=all_messages)
# Get the generated chat response from the model
system_message = response.choices[0].message.content
# all_messages.append(system_message.to_dict())
all_messages.append({"role": "assistant", "content": system_message})
chatbot_responses = [] # Initialize the list outside the loop
# user_input = ""
for message in all_messages:
print(f"Message: {message}")
# print(f"role: {message['role']}")
if 'role' in message and 'content' in message:
# print(f"role: {message['role']}")
if message['role'] == 'user':
user_input = message['content']
print(f"ui: {user_input}")
elif message['role'] == 'assistant':
chatbot_responses.append([user_input, message['content']])
# chatbot_responses.append(message['content'])
# print(f"hdjdkdkksdk: {message['content']}")
print(f"Assistant response appended: {message['content']}")
print(f"cbr: {chatbot_responses}")
# For English input, use English language voice
tts = gTTS(text=chatbot_responses[-1][1], lang='en', slow=False)
tts.save("output_audio.mp3")
# tts = gTTS(text=chatbot_responses[-1][1], lang=language, slow=False)
# detected_language = detect(user_input)
# if detected_language == 'hi':
# # For Hindi input, use the Hindi language voice
# tts = gTTS(text=chatbot_responses[-1][1], lang='hi', slow=False, lang_check=False)
# tts.save("output_audio.mp3")
# else:
# # # For English input, use English language voice
# tts = gTTS(text=chatbot_responses[-1][1], lang='en', slow=False)
# tts.save("output_audio.mp3")
return [chatbot_responses[-1]], "output_audio.mp3" # Wrap the chatbot response in a list
# return chatbot_responses, "output_audio.mp3"
# out1 = gr.Audio("output_audio.mp3")
css_styles = """
footer { visibility:hidden; }
.audio_container { height: 100px; }
.svelte-1e89no8 { padding: 10px; }
.input_text_container { height: 100px; }
@media only screen and (max-width: 450px) { .input_text_container { display: none; } }
"""
with gr.Blocks(theme=gr.themes.Monochrome(font=[gr.themes.GoogleFont("Inter"), "sans-serif"],
spacing_size=gr.themes.sizes.spacing_md,
radius_size=gr.themes.sizes.radius_md),
css=css_styles,
title="NanoAI Voice Assistant") as demo:
# chatbot = gr.Chatbot().style(height=450) # Pass the all_messages list to the Chatbot widget
chatbot = gr.Chatbot(clear_on_refresh=True).style(height=450)
out1 = gr.Audio("output_audio.mp3", autoplay=True, label="Voice Response ")
with gr.Row():
with gr.Column(scale=0.35):
audio_input = gr.Audio(source="microphone", type="filepath", label="Record your question (Voice)", elem_classes="audio_container")
with gr.Column(scale=0.65):
text_input = gr.Textbox(label="Or Type your question here (Chat)",
placeholder="What would you like to ask the bot...",
elem_classes="input_text_container")
with gr.Row():
with gr.Column(scale=0.50):
text_button = gr.Button("Send a Message")
with gr.Column(scale=0.50):
reset_button = gr.Button("Clear ❌")
text_button.click(transcribe, [audio_input, text_input], [chatbot, out1])
text_button.click(lambda x: gr.update(value=''), [], [text_input])
text_button.click(lambda: None, None, audio_input),
text_button.click(lambda: None, None, out1),
reset_button.click(lambda: None, None, chatbot),
reset_button.click(lambda: None, None, out1)
# audio_input = gr.Audio(source="microphone", type="filepath")
demo.launch()