SPEAK TOOL · TTS · INLINE AUDIO
voice-mcp
@YINGLIANCHUN
Give the Agent a speak tool that can be called directly, so that the reply can be played with a dedicated sound.
voice-mcp encapsulates TTS into a speak(text) tool, allowing Agents such as Claude to actively call sounds and display the player directly in the conversation.
Project address (can be copied to AI):https://github.com/Yinglianchun/voice-mcp
PROJECT INTRO
Project introduction
voice-mcp provides speak(text) MCP tools to switch between DashScope Qwen-TTS VC and ElevenLabs, and playback the results through the MCP Apps inline player and real-time visualization panel.
This repository is an MIT fork of garan0613/voice-mcp, retaining the original behavior and adding Provider switching, ElevenLabs and visualization functions, so it is not marked as original.
- Suitable for:People who hope that MCP Agents such as Claude and Codex will actively call exclusive sounds.
- Platform:Cloudflare Workers and clients supporting MCP Apps.
- Usage:Deploy the Worker, configure the Voice Provider, and then register the service with the MCP client.
- License:MIT; based on garan0613/voice-mcp.
COMMENTS & FEEDBACK
Comments and Feedback
People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.
The message is waiting for review and will be publicly displayed here after approval.
SOURCE & CREDIT
Atlas is responsible for the introduction and navigation, and the use still returns to the original author.
We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.
Reading public comments...