mberg/kokoro-tts-mcp

Overview

Kokoro Text to Speech (TTS) MCP Server is a Python-based server that exposes text-to-speech functionality through the Model Context Protocol. It allows MCP-compatible clients to generate audio from text input using the Kokoro TTS model.

Best for

Best for
Developers needing a straightforward TTS server for MCP-based tools

Use cases

• Integrating TTS into MCP-compatible AI agents
• Generating spoken responses from language model outputs
• Adding voice output to automation scripts

How to use

Install

uv run mcp-tts.py

Tools exposed

• uv
• brew
• ffmpeg

Example client config

"kokoro-tts-mcp": {\n      "command": "uv",\n      "args": [\n        "--directory",\n        "/path/toyourlocal/kokoro-tts-mcp",\n        "run",\n        "mcp-tts.py"\n      ],\n      "env": {\n        "TTS_VOICE": "af_heart",\n        "TTS_SPEED": "1.0",\n        "TTS_LANGUAGE": "en-us",\n        "AWS_ACCESS_KEY_ID": "",\n        "AWS_SECRET_ACCESS_KEY": "",\n        "AWS_REGION": "us-east-1",\n        "AWS_S3_FOLDER": "mp3",\n        "S3_ENABLED": "true",\n        "MP3_FOLDER": "/path/to/mp3"\n      } \n    }

Notes

Kokoro Text to Speech (TTS) MCP Server is a Python-based server that exposes text-to-speech functionality through the Model Context Protocol. It allows MCP-compatible clients to generate audio from text input using the Kokoro TTS model.

78 stars on GitHub. Last updated 2025-09-12. Licensed Apache-2.0.

Use cases

• Integrating TTS into MCP-compatible AI agents
• Generating spoken responses from language model outputs
• Adding voice output to automation scripts

Pros

• Simple MCP interface for TTS integration
• Lightweight Python implementation
• Open source with permissive license

Cons

• Small community and limited documentation
• May lack advanced features like voice cloning
• Requires MCP client to use

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.