nice.mp4
Follow these instructions in order to get the application running.
- Install requirements
- Clone this repository to your local machine using the following command
git clone https://github.com/AuracleTech/piai.git
- Navigate to the project directory
cd piai
- Install OpenAI Whisper
pip install -U openai-whisper
- Install pipreqs to generates the dependencies
pip install pipreqs
- Generate the dependencies file
pipreqs . --force
- Install the dependencies
pip install -r requirements.txt
- Launch the app
python src/main.py
- Have a chat with your new voice assistant 🌟
The application uses 3 threads
Recorder.py
records vocal inputs torecordings
folder.Transcriber.py
transcribes the files and sends the transcript to the interpreter.Interpreter.py
transmits what you said to Pi.
You can use GPT to determine if Pi should respond to the vocal input, to use it follow these steps.
-
Get an OpenAI API Key
-
Create a .env file in the root directory and add the following variable
OPENAI_API_KEY=your-openai-api-key-here
- Uncomment the code in interpreter.py and/or modify it to your liking.
Feel free to open an issue if you have any questions, suggestions or issues.