Skip to content

Latest commit

 

History

History
46 lines (29 loc) · 1.33 KB

README.md

File metadata and controls

46 lines (29 loc) · 1.33 KB

Voice Assistant

A Voice Assistant leveraging the Gemini API for long-term memory, designed to provide intelligent and personalized interactions. This assistant can process voice commands, store and retrieve contextual data, and deliver a highly interactive user experience.

Features

  • Long-term Memory: Stores user-specific data and context for personalized interactions.
  • Voice Recognition: Processes voice commands and responds naturally.
  • Gemini API Integration: Utilizes the Gemini API for advanced capabilities and extended functionality.
  • Modular Design: Easy to extend with new features or capabilities.

Installation

Prerequisites

  • Python 3.8+
  • Virtual environment tool (optional but recommended)
  • Required Python libraries (see requirements.txt)

Setup

  1. Clone this repository: 
    git clone https://github.com/yourusername/voice-assistant.git
cd voice-assistant
  2. Create and activate a virtual environment (optional but recommended):

python -m venv venv source venv/bin/activate # On Windows, use venv\Scripts\activate

  1. Install dependencies:

pip install -r requirements.txt

Set up the Gemini API:

Sign up for a Gemini API key here. Add your API key to a .env file in the project root:

GEMINI_API_KEY=your_api_key

Usage

Run the voice assistant: python main.py