There are 1 repository under react-speech-recognition topic.
HciTube - A Video Sharing Platform
The Clone of Google with search functionalities for different categories like All Search, Images search, Videos search, news Search and Voice Search .
Voice Assistant with an ever-growing list of available commands!
It is a Speech to text converter made in vite+reactjs , react speech recognition library
Question Bank Generator uses a crowd sourcing model to prepare question banks from a large pool of objective questions. QBaG provides an interface for paper setters and academicians to generate reliable question papers using our automated and robust system.
A MERN stack web app for translating text between multiple languages. Features a clean UI, automatic language detection, speech-to-text input, and text-to-speech output. Utilizes Google Translate API and MongoDB for storing translation data. Designed for scalability, efficiency, and robust performance.
Bilimgual is a web service designed for creating and taking tests in two languages. https://linear.app/bilingual/team/BIL/all
React Application that listens to human speech, translates into another selected language and speaks the translated language
This new browser extension changes how you talk to ChatGPT. You can now have voice conversations with it easily.
Next.js web app leveraging Google Gemini AI for text translation from user input or uploaded files into multiple languages. Built for seamless translation experiences.
Convert speech to text effortlessly and copy with ease with our app.
This is a web application that allows users to transcribe speech into text using the browser's speech recognition capabilities.
An app to assign tasks to departments and monitor them.
That project is mainly provife to four language to talk and cout some word ,its a same in google speeks feature.,
A React application that translates speech and converts it to readable text. Added functionality to start and stop listening , users can copy the text to their clipboard as well.
React GUI for controlling a table tennis robot
An AI-powered web app that acts as a virtual assistant for car dealership interactions. The app uses speech recognition and GPT-3.5 for real-time conversations, helping customers with car-related inquiries and providing voice responses.
Application that can convert speech to text, save transcripts, and support multiple languages
Depression Diagnoser is a web application that assesses and diagnoses depression levels through user responses and facial expression analysis, providing a personalized evaluation.
"Practice-Your-Self" is a user-friendly web application designed to help individuals improve their speaking skills. With the click of a button, users can start and stop speaking.
Flow Chat Widget is a versatile and user-friendly chat interface that allows seamless communication between users and bots. Designed for optimal usability, this widget is movable, enabling users to place it anywhere on their screen for a customizable chat experience.
This is a speech recognition app... where I have conditionally rendered some text by detecting users speech.. technology used - Nextjs, react-speech-recognition, Tailwind Css
Simple react project which converts input audio speech from device microphone into text(required code in master branch).
I built this website using TypeScript to practice my skills. It's designed for transcribing audio to text and then translating the transcribed text into various languages.
This is the repo of text-translator frontend , it is the assignment of Punt-Partner company.
AI Voice and Text Translation App Created with Next JS
Voice to text using react, vite, ts, react speech recognition, bootstrap
This is frontend only
This is the React Library Based Project where Speech is Converted into Text. That can be used as utility
A simple speech-recognition webapp designed using vite-react
"G-Translate" is a cutting-edge AI SaaS language translation tool developed using Next.js and TypeScript. It enables users to translate spoken words into different languages, making it an invaluable resource for those learning new languages or needing real-time translation.
This repository has two reusable speech-to-text converter components. The first utilizes React Speech Recognition, while the second utilizes the Web Speech API directly. These components are designed for easy integration into future projects. It's important to note that React Speech Recognition internally leverages the Web Speech API.