Touch Controlled Talking Clock for PSoC Analog Coprocessor

Basic Text To Speech with Vanilla JS

Live Musical Vocoder Implementation for Windows

La canción de los elefantes que se balanceaban. En un bucle infinito

Wechat-autoreply

Pi based majordomo displaying events on 7segments , OLED, LCD displays, saying messages....

A speech synthesis and recognition library that is cross-platform, accessible from Java and C++, and has a very small API. Uses CMU Sphinx4 and FreeTTS internally.

implementation of Zeyu et al.「FFTNET: A REAL-TIME SPEAKER-DEPENDENT NEURAL VOCODER」

(Japanese version)(chat-gpt-reader-chrome-extension)(Created by:🐧 💨💨💨 @s4na s4na Satoshi Nabetani Japan)MIT License

A voiced wiki map

Microcontroller Voice Modulator based on STM32F407 board, alongside with sound visualization.

Making an AI voice from my speaking

Flask app to synthesise a vowel based on formant values. Backend for react-klatt.nyoeghau.com

generate nasal voice /na/ /ma/ sound by two tubes model and nasal effect source

A plugin to use the Mac's text to speech from Sublime Text 3.

The project uses the browser's speech synthesis feature to transform text typed by the user into voice.

This is a simple text to speech translator developed using python

repositories table related to vocal tract tube model.

Image Classification/Natural Language Processing: An AI-enabled conversational chatbot that helps diabetic patients in detecting diabetic retinopathy, give informations about the symptoms, treatments, researches going on, all sort of information about the disease. This patient-care app also find the nearest eye hospital near the patient for emer…

A project for distinguishing synthesized voices from natural voices. README is a paper discussing the motivation and results of the project. The techical implementation can be found in the jupyter notebook file.