MCPs tagged with # text-to-speech

Speech.sh provides robust text-to-speech capabilities from the command line by leveraging OpenAI's API and offers Model Context Protocol (MCP) compatibility for integration with AI assistants. Supporting multiple voice options, adjustable speech speed, and both tts-1 and tts-1-hd models, it ensures seamless audio conversion and playback. Flexible API key management, auto-caching, and reliable retry logic make it suitable for diverse environments. Additional features include security-focused processing, dependency validation, and compatibility with both ffmpeg and mplayer audio players.

• ⭐ 5
• MCP
• j3k0/speech.sh

mcp-hfspace allows users to connect Hugging Face Spaces with minimal setup, enabling these spaces as MCP-compatible endpoints for tools like Claude Desktop. It facilitates automatic configuration, efficient file handling, support for private spaces, and flexible working directory management. The project supports Image Generation, Vision, and Text-to-Speech models, operating in Claude Desktop mode for streamlined file and image interaction.

• ⭐ 366
• MCP
• evalstate/mcp-hfspace

Kokoro Text to Speech MCP Server provides a text-to-speech API that generates MP3 audio files from text input, with support for multiple voices and speech parameters. It is designed for compatibility with Model Context Protocol (MCP), allowing for easy integration and configuration in MCP-based workflows. Generated audio files can be stored locally or uploaded to AWS S3, and the server includes client utilities for interaction, as well as configurable environment options for deployment. The solution leverages Hugging Face Kokoro-TTS models and supports both direct use and cloud-friendly workflows.

• ⭐ 67
• MCP
• mberg/kokoro-tts-mcp