Huawei Grad-TTS for Chinese

Fluent-ish SSML Generator

A Cinnamon panel applet that combines keyboard layout switching with voice input capabilities powered by OpenAI Whisper or local Whisper servers.

This is an application that asks us for the input of text and converts it into audio

This project is a Speech-to-Text and PDF Converter with a modern, visually appealing interface. It allows users to record speech in Hindi or English, converts it to text, and provides options to download the content as a PDF or image. Featuring advanced design, dynamic backgrounds, and accessibility, it’s both functional and engaging.

Hubitat to PI Controller talking ,chimes, alarm, siren, button , GPIO , Temp , volts, Rasbery Pi model detection

Treine a sua oratória. Uma tema e uma estrutura serão gerados de forma aleatória. Com o auxílio do cronômetro, fale por 1 minuto.

Bare-handed procedural speech synthesis.

Desktop Program that includes: "NLP filter to prevent a chatbot from going off-topic." " Voice Recognition Platform" " Talking Motor using GPT4ALL Falcon 4.0B "Graphical Interface for Hand Control" " Events Player"

💬 Интерактивный тренажер произношения исностранного языка

Got a soar throat? Well, this is just for you!

Octave speech recognition using correlation.

A simple generic TTS speak simulator ROS Node. This is a MIRRORED REPOSITORY Refer to the GitLab page for the origin.