Failed to install on macOS

[jifbrodeur]

On first try, pip failed to find whisper==20231117, I changed it to openai-whisper and it failed Building wheels for collected packages: pyaudio
DEPRECATION: Building 'pyaudio' using the legacy setup.py bdist_wheel mechanism, which will be removed in a future version. pip 25.3 will enforce this behaviour change. A possible replacement is to use the standardized build interface by setting the --use-pep517 option, (possibly combined with --no-build-isolation), or adding a pyproject.toml file to the source tree of 'pyaudio'. Discussion can be found at pypa/pip#6334
Building wheel for pyaudio (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py bdist_wheel did not run successfully.
│ exit code: 1
╰─> [14 lines of output]
Thanks for your help

[VideotronicMaker]

Unfortunately I do not have access to my system. I can offer this but I cant say if it will help:

KITT Voice Assistant
This is a Python-based voice assistant that uses a local large language model (LLM) server (like LM Studio) for generating responses and the OpenAI Whisper model for speech-to-text transcription.
Features
Voice-activated: Start recording by pressing the 'B' key.
Text input: Type your input directly by pressing the 'M' key.
Local LLM: Connects to a local inference server (e.g., LM Studio), so no OpenAI API key is needed for the chat functionality.
Text-to-Speech: Responds with voice output (currently configured for a specific Windows voice).
Setup and Installation
These instructions will guide you through setting up the project on your local machine.

1. Prerequisites
   Python 3.8 or newer.
   A local LLM inference server running and accessible at http://localhost:1234. LM Studio is a great option.

2. Clone the Repository
   First, clone this repository to your local machine or download the files.
   git clone
   cd

3. Create a Virtual Environment (Recommended)
   It's highly recommended to use a virtual environment to avoid conflicts with other Python projects.

Windows

python -m venv venv
venv\Scripts\activate

macOS / Linux

python3 -m venv venv
source venv/bin/activate

4. Install System Dependencies (For PyAudio)
   This is the most critical step. PyAudio requires the PortAudio C library to be installed on your system. Please follow the instructions for your operating system.
   On Windows:
   The easiest way is to ensure you have the Microsoft C++ Build Tools installed.
   Download the Visual Studio Installer.
   When installing, select the "Workloads" tab and check the box for "Desktop development with C++".
   Proceed with the installation. This will provide the necessary compilers for pyaudio.
   On macOS:
   Use Homebrew to install PortAudio.
   brew install portaudio

On Linux (Debian/Ubuntu):
Use the apt package manager to install the PortAudio development files.
sudo apt-get update
sudo apt-get install portaudio19-dev libasound2-dev

5. Install Python Packages
   Once the system dependencies are in place, you can install all the required Python packages using the requirements.txt file.
   pip install -r requirements.txt

6. Run the Application
   After installation, you can run the main script.
   python main.py

Important: The script uses the keyboard library, which may require administrator (Windows) or root/sudo (Linux/macOS) privileges to detect key presses system-wide. If you have issues, try running the terminal or command prompt as an administrator.
The text-to-speech engine is currently hardcoded to a specific Windows voice (TTS_MS_EN-GB_HAZEL_11.0). This will need to be changed or removed if you are on a different OS or don't have this voice installed.