Skip to content

fahdmirza/gemini_voice_assistant

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 

Repository files navigation

image

Gemini Voice Assistant

A simple voice assistant built using the Gemini API and Python.

Table of Contents

About Features Requirements Installation Usage License

About

This project is a basic implementation of a voice assistant using the Gemini API. It allows users to interact with the Gemini model using voice commands.

Features

Key Features Real-time voice interaction with the Gemini model Supports audio input and output Simple and easy-to-use interface

Requirements

Dependencies

Python 3.11 or later

Gemini API key (obtainable from the Google Cloud Console) https://aistudio.google.com/

PyAudio library (install using pip install pyaudio)

WebSockets library (install using pip install websockets)

Installation

Steps to Install

Clone the repository using: git clone https://github.com/fahdmirza/gemini_voice_assistant.git

Install the required libraries using: pip install -r requirements.txt

Set up your Gemini API key as an environment variable using: export GEMINI_API_KEY=your-api-key-here

Usage

Running the Voice Assistant Run the voice assistant using: python3 gemini_voice_assistant.py Start speaking to interact with the Gemini model Use voice commands to perform tasks or ask questions

License

This project is licensed under the Apache-2.0 License. See LICENSE for details.

About

An AI-Powered Voice Assistant Using Gemini Flash

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages