This library provides audio interface with OpenAI endpoint.
Project description
Wyn Voice: A Conversational AI and Audio Processing Library
Introduction and Motivation
Wyn Voice is a Python library designed to simplify the process of creating conversational AI applications that leverage OpenAI's GPT models. The library provides an easy-to-use interface for generating responses to user inputs and includes functionality for recording and processing audio, making it suitable for building interactive voice-based applications.
Directory Structure
The project directory is organized as follows:
.
├── pyproject.toml
├── README.md
└── wyn_voice
└── chat.py
pyproject.toml
: Contains the project's dependencies and other configuration settings.README.md
: This file, providing an overview and usage instructions.wyn_voice
: A folder containing the main library code.chat.py
: The script defining theChatBot
andAudioProcessor
classes.
Example Usage
To get started with Wyn Voice, follow these steps:
Installation
First, install the necessary packages using pip:
pip install wyn-voice pyautogen pydub openai
Using the ChatBot Class
The ChatBot
class allows you to interact with OpenAI's GPT models to generate responses based on user input.
from wyn_voice.chat import ChatBot
# Initialize the ChatBot with your OpenAI API key
api_key = 'your-openai-api-key'
chatbot = ChatBot(api_key)
# Generate a response from the chatbot
prompt = "Hello, how are you?"
response = chatbot.generate_response(prompt)
print("ChatBot:", response)
# Retrieve the conversation history
history = chatbot.get_history()
print("Conversation History:", history)
Using the AudioProcessor Class
The AudioProcessor
class provides functionality to record audio, process it, and interact with the ChatBot
.
from wyn_voice.chat import ChatBot, AudioProcessor
# Initialize the ChatBot with your OpenAI API key
api_key = 'your-openai-api-key'
chatbot = ChatBot(api_key)
# Initialize the AudioProcessor with the ChatBot
audio_processor = AudioProcessor(chatbot)
# Record audio and generate a response
transcript = audio_processor.process_audio_and_generate_response()
print("Transcript:", transcript)
# Record audio and get the transcribed text
text = audio_processor.voice_to_text()
print("Transcribed Text:", text)
# Convert text to speech and save it as an mp3 file
response_text = "This is a test response."
output_file = audio_processor.text_to_voice(response_text)
print("Saved audio response to:", output_file)
# Play the saved audio file
audio_processor.play_audio(output_file)
Author
Yiqiao Yin
Site
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for wyn_voice-0.1.9-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b4f89e5173db58bbd87bdd97ef3448988be87d0db2e67f700b7ccffafe2d56a0 |
|
MD5 | 12df968b669dabdf9f3e05ec3ccfe3a6 |
|
BLAKE2b-256 | 4775e403f14394c60f69d3d8cf8ef63bf1b2d9f958c605d9b61ef9bcf5affd7a |