Install FFmpeg Essentials
set ffprobe=(ffmpeg-6.0-essentials_build\bin)
Rename .env.sample
to .env
Fill in (OpenAI API Key) and (...FFmpeg\ffmpeg-6.0-essentials_build\bin)?
set NO_PROXY=localhost,127.0.0.1,::1
set path=%path%;D:\Downloads\Tools\FFmpeg\ffmpeg-6.0-essentials_build\bin
python -m venv .venv
pip install -r requirements.txt
python main.py
My Voice Assistant is an AI-powered chatbot built with the collaboration of several APIs, including ChatGPT, Whisper API, Gradio, and Microsoft's SpVoice TTS API. It can understand natural language commands and provide helpful responses to various queries.
The Voice Assistant is equipped with a wide range of features that can be accessed through voice commands. Here are some of the key features:
-
Answering questions: The Voice Assistant can provide answers to general knowledge questions, such as "What is the capital of France?" or "What is the weather like in New York today?"
-
Recommendations: The Voice Assistant can suggest movies, TV shows, books, and restaurants based on your preferences.
-
Productivity: The Voice Assistant can perform tasks such as creating a to-do list or scheduling an appointment for your calendar.
-
Entertainment: The Voice Assistant can write poems or tell jokes upon request.
- Python 3.x
- Gradio
- ChatGPT API
- win32com (for Windows users only)
The Voice Assistant was built using the following APIs:
-
ChatGPT: ChatGPT is a large language model trained by OpenAI that can understand natural language commands and provide helpful responses.
-
Whisper API: Whisper API converts speech to text.
-
Gradio: Gradio is a user interface API that allows users to interact with the Voice Assistant through a web-based interface.
-
Microsoft's SpVoice TTS API: This API is used to provide text-to-speech functionality, allowing the Voice Assistant to speak responses out loud.
To use the Voice Assistant, simply open the web-based interface provided by Gradio and click on the microphone button and speak to your assistant!. You can also edit your recorded questions to highlight the best parts. The Voice Assistant will listen to your commands and provide responses as needed.
- Clone the repository:
git clone https://github.com/DonGuillotine/chatGPT_whisper_AI_voice_assistant.git
python -m venv .venv
- Install the required Python packages:
pip install -r requirements.txt
- Sign up for ChatGPT API key from https://beta.openai.com/signup/, set
.env
runpython main.py
, notmain.py
orpy main.py
, because of not running under virtual environment
Contributions to this project are welcome. If you encounter any bugs or issues, please open an issue in the repository. If you would like to contribute code, please fork the repository and submit a pull request.
The Voice Assistant built with ChatGPT, Whisper API, Gradio, and Microsoft's SpVoice TTS API is a powerful tool that can help with a wide range of tasks, from answering general knowledge questions to scheduling appointments. It is easy to use and can be accessed through a web-based interface.