This Django project allows converting text to audio files and saving them.Conversion of text to speech in multiple languages.

Jetbot Voice to Action Tools is a set of ROS2 nodes that utilize the Jetson Automatic Speech Recognition (ASR) deep learning interface library for NVIDIA Jetson

Automated reels/shorts creating program that generates content about realtime trending topics

Image Caption Generator

An open-source project that uses cutting-edge NLP models and real-time web search to provide dynamic voice query responses. Features include speech-to-text with Nemo, text generation with Mistral-7B, DuckDuckGo search integration, and text-to-speech with edge-tts, all in a user-friendly Gradio interface.

This project uses YOLO v8 for real-time object detection in images, providing voice feedback on the detected objects' positions. Powered by the gTTS API, it offers seamless integration and enhanced user experience.

Useful applications using Python 3

Open Translator: Speech To Speech and Speech to text Translator with voice cloning and other cool features

The EuRecog gesture recognition app is a hand gesture recognition system that lets a user customize ten unique hand gesture signs with questions, then based on the gesture provided by said user in usage sends the question attached to that gesture to an LLM (Open AI's gpt-3.5-turbo-instruct) then provides an answer in both text and audio form.

Repository to save the code for the software and hardware prototype for Lego Yoshi, a proposed expansion to the Lego Super Mario interactivity using OpenAI's GPT 3.5 Turbo API

readLites makes reading fun and easy! It uses smart technology to show pictures and pick out important ideas from stories. This helps you understand and enjoy books better!

A seamless platform to capture and organize your thoughts effortlessly through audible notes

A basic web text-to-speak with Flask, gTTS and Python

This project aims to assist visually impaired individuals by providing a solution to convert images into spoken language. Leveraging deep learning and natural language processing, the system processes images, generates descriptive captions, and converts these captions into audio output.

I am currently engaged in study and development of a virtual assistant aimed to enchant my daily tasks through various automation capabilities. This assistant I will have the ability to control music playback, schedule appointments, set timer and other useful functions.

🎥 Memory Machine 3.5 (Object Access & Storage Facilitator) Development for Horizon Digital Economy Research at University of Nottingham. Deployed using Python3, Open-CV, Arduino & gTTS.

متن به صدا | Text To Speech 😊🤩

API to convert pdf files to audiofiles

AUDVI - AI Arduino Object Detector for the Visually Impaired

A talking assistant that uses GPT-3 to generate audio responses to the audio input.