MOSS-TTSD is a spoken dialogue generation model designed for expressive multi-speaker synthesis. It features long-context modeling, flexible speaker control, and multilingual support, while enabling zero-shot voice cloning from short audio references.

A fast, lightweight, and extensible RWKV chat UI powered by Flutter. Offline-ready, multi-backend support, ideal for local RWKV inference.

Преобразование голоса на основе VITS. Ориентировано на простоту, качество и производительность.

Speech-to-text, text-to-speech with ElevenLabs

This repo contains code to interface robot with PiCamera, transistors (for switching 12V high brightness LEDs), Ultrasonic Distance Sensor and Speaker (for text to speech)

Jednoduchá Text To Speech aplikace vytvořená s pomocí Azure a Reactu.

Speech tools built into the browser to make a web page that can speak anything.

This repo presents an adventure of approaches with run configurations for converting a list of numbers to french format strings(words)

Generate painless, realistic sounding audiobooks from text files to add some sanity to your reading workload.

Tamil learning protocol

Text to Speech Demo in browser using Web Speech API

Chat with & listen to your PDFs locally. A full-stack RAG assistant featuring synchronized Text-to-Speech (TTS), AI document chat, and 100% local execution for total privacy.