Explore live open-source projects and AI models.

MSSpeechServer is a REST server based on the Microsoft Speech Platform that provides text-to-speech (TTS) functionality for Windows. This project is designed to run on the Linux x86_64 platform and supports Docker images. It provides two main APIs for reading voice libraries and generating TTS.

Docker for multiple TTS Engines with a GRadio interface

Magic Chat 🎙️ is a #real-time AI voice chat app with expressive characters using #OpenAI, #ElevenLabs, XTTS, #Ollama, #Kokoro TTS, #WebRTC, and #Docker, supporting #games, #stories, and #local or #cloud models.

🗣️ Qwen3-TTS All-in-One Docker: Web UI + REST API + MCP Server | 10 Languages | Voice Clone/Design/Custom | GPU Auto-Management

🎙️ All-in-One Docker image for Kokoro-82M TTS - Web UI, REST API, WebSocket, Streaming, Batch, MCP

Dockerized Tabletop Simulator

Lightweight Chinese TTS system; generate speech from text, supports multiple models (Kokoro, MOSS, ZipVoice), WebSocket streaming, Web UI, Docker-ready.

🎙️ Production-ready Docker deployment for VoxCPM TTS service with GPU support, REST API, Web UI, and MCP protocol integration

Dockerized FastAPI wrapper for OmniVoice — zero-shot TTS for 600+ languages with voice cloning, voice design, and OpenAI-compatible API. GPU & CPU support.

Docker container that gives your IP phone (e.g., FRITZ!Box) a voice + AI. It answers calls, speaks with fast local TTS, and triggers automations (n8n) via simple webhooks. Copy the sample config, run docker-compose, and start talking.