# Text-to-Speech

This project implements the MCP server for the Typecast API, providing a standardized way for MCP clients to interact with the text-to-speech service.

A text-to-speech MCP server based on the built-in say command in macOS

MiniMax-MCP is a multi-functional server project that provides API services such as text-to-speech, video generation, and image generation, supporting developers to integrate advanced multimedia features.

MiniMax's official Model Context Protocol (MCP) server supports interactions with APIs such as text-to-speech, video/image generation.

MCPollinations is a multimodal AI service based on the Model Context Protocol (MCP) that supports generating images, text, and audio through the Pollinations API. It offers a lightweight service that does not require authentication, is compatible with multiple AI models, and supports image saving and Base64 encoding return.

A voice generation MCP server based on Minimax AI and Amazon S3, providing text-to-speech functionality and automatically uploading audio files to cloud storage

This is an MCP server project based on Node.js. It integrates AI assistants with the Bouyomi-chan voice synthesis software through the Model Context Protocol to provide text-to-speech functionality.

A simplified MCP server based on the Chatterbox TTS model, providing text-to-speech generation and automatic playback functions, supporting real-time progress notifications and automatic model loading.

The Minimax MCP Tools is an MCP server implementation integrating the Minimax API, providing AI image generation and text-to-speech functions, and supporting seamless integration with the Windsurf editor.

Speech MCP is a voice interaction extension designed for Goose, providing real-time voice recognition, text-to-speech, and audio visualization functions.

Blabber-MCP is an MCP server based on the OpenAI Text-to-Speech API, providing voice output functionality for LLMs.

A text-to-speech tool based on the MCP server and OpenAI TTS SDK, supporting local environment playback.

A text-to-speech MCP server based on the Kokoro TTS model, providing high-quality speech synthesis services

The MCP server for VOICEPEAK text-to-speech, supporting functions such as speech synthesis, playback, and pronunciation dictionary management

A multi-functional TTS server based on the MCP framework that integrates the Kokoro local TTS and the OpenAI cloud TTS engine, supporting real-time audio streaming, voice customization, and playback control.

Rime MCP is a text-to-speech service based on the Rime API, which realizes voice synthesis and playback functions through the system's native audio player.

An MCP server that provides comprehensive audio playback functionality for macOS, supporting system sounds, text-to-speech, and custom audio file playback, suitable for MCP clients such as AI assistants.

A high-quality text-to-speech tool and MCP service based on the OpenAI TTS API