MCP.so
Sign In

VoiceStudio MCP Server

@NewAITees

About VoiceStudio MCP Server

No overview available yet

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "VoiceStudio-MCP-server": {
      "command": "uv",
      "args": [
        "run",
        "src.main",
        "--host",
        "127.0.0.1",
        "--port",
        "8080",
        "--debug"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is VoiceStudio MCP Server?

A Python‑based MCP server that provides text‑to‑speech synthesis using the Kokoro engine. It is designed for developers who want to integrate Japanese TTS capabilities into MCP‑compatible applications, or to build and test TTS workflows locally.

How to use VoiceStudio MCP Server?

Clone the repository, set up a virtual environment with uv, install dependencies, and optionally configure Kokoro or use mock mode (MOCK_TTS=true). Start the server with python src/main.py; use --dev or --log-level debug for development. A Docker setup is also available via make build and make up.

Key features of VoiceStudio MCP Server

  • MCP protocol integration for TTS
  • Kokoro speech synthesis engine support
  • Mock mode for development without Kokoro
  • Docker container with multi‑architecture builds
  • Japanese TTS via PyOpenJTalk, MeCab, and fugashi
  • Debug logging, request/response logging, and debugging tools

Use cases of VoiceStudio MCP Server

  • Adding voice output to MCP‑based assistants or workflows
  • Developing and testing TTS features without a physical Kokoro engine
  • Running a production‑ready TTS microservice behind Docker
  • Customising Japanese TTS with MeCab dictionaries

FAQ from VoiceStudio MCP Server

What dependencies are required?

Python 3.10+, uv, Git, Docker and Docker Compose. For real TTS, the Kokoro engine is needed; mock mode works without it.

How do I set up Japanese TTS components?

Install PyOpenJTalk (uv pip install pyopenjtalk), MeCab, and fugashi with unidic‑lite/ipadic. On Windows, run python mecab_windows_setup.py to configure paths.

Can I run the server without the Kokoro engine?

Yes. Set MOCK_TTS=true to use a simulation. This is useful for development or testing.

What environment variables control the server?

OPENAI_API_KEY, CLAUDE_API_KEY, LOG_LEVEL, MOCK_TTS, and PORT (default 8080).

How do I debug issues?

Use --log-level debug (or env LOG_LEVEL=DEBUG). For request/response logging add --log-requests. Inside code, pdb breakpoints work. Docker logs are available via docker logs kokoro-mcp-server.

Frequently asked questions

What dependencies are required?

Python 3.10+, `uv`, Git, Docker and Docker Compose. For real TTS, the Kokoro engine is needed; mock mode works without it.

How do I set up Japanese TTS components?

Install PyOpenJTalk (`uv pip install pyopenjtalk`), MeCab, and fugashi with unidic‑lite/ipadic. On Windows, run `python mecab_windows_setup.py` to configure paths.

Can I run the server without the Kokoro engine?

Yes. Set `MOCK_TTS=true` to use a simulation. This is useful for development or testing.

What environment variables control the server?

`OPENAI_API_KEY`, `CLAUDE_API_KEY`, `LOG_LEVEL`, `MOCK_TTS`, and `PORT` (default 8080).

How do I debug issues?

Use `--log-level debug` (or env `LOG_LEVEL=DEBUG`). For request/response logging add `--log-requests`. Inside code, `pdb` breakpoints work. Docker logs are available via `docker logs kokoro-mcp-server`.

Comments

More Other MCP servers