VOICEVOX

by dosugamea

3 stars

Not rated

GitHub

About

Connects AI systems to VOICEVOX text-to-speech engine for Japanese voice synthesis, supporting both default transport and Server-Sent Events with configurable speaker options.

Details

Author: dosugamea
Repository: Dosugamea/voicevox-mcp-server
GitHub stars: 3
License: MIT License
Categories: Design, AI, API, Infrastructure, Frontend

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name VOICEVOX

Command (node, npx, python, etc.) npx
Arguments
- Argument 1 -y
- Argument 2 @highlight/mcp-server
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {
                "PULSE_SERVER": "unix:/mnt/wslg/PulseServer",
                "SDL_AUDIODRIVER": "pulseaudio",
                "VOICEVOX_API_URL": "http://host.docker.internal:50031",
                "VOICEVOX_SPEAKER_ID": "919692871"
            },
            "args": [
                "/c",
                "docker",
                "run",
                "-i",
                "--rm",
                "-v",
                "/mnt/wslg:/mnt/wslg",
                "-e",
                "PULSE_SERVER",
                "-e",
                "SDL_AUDIODRIVER",
                "-e",
                "VOICEVOX_API_URL",
                "-e",
                "VOICEVOX_SPEAKER_ID",
                "your-local-docker-image-name"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {
                "PULSE_SERVER": "unix:/mnt/wslg/PulseServer",
                "SDL_AUDIODRIVER": "pulseaudio",
                "VOICEVOX_API_URL": "http://host.docker.internal:50031",
                "VOICEVOX_SPEAKER_ID": "919692871"
            },
            "args": [
                "/c",
                "docker",
                "run",
                "-i",
                "--rm",
                "-v",
                "/mnt/wslg:/mnt/wslg",
                "-e",
                "PULSE_SERVER",
                "-e",
                "SDL_AUDIODRIVER",
                "-e",
                "VOICEVOX_API_URL",
                "-e",
                "VOICEVOX_SPEAKER_ID",
                "your-local-docker-image-name"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {
                "PULSE_SERVER": "unix:/mnt/wslg/PulseServer",
                "SDL_AUDIODRIVER": "pulseaudio",
                "VOICEVOX_API_URL": "http://host.docker.internal:50031",
                "VOICEVOX_SPEAKER_ID": "919692871"
            },
            "args": [
                "/c",
                "docker",
                "run",
                "-i",
                "--rm",
                "-v",
                "/mnt/wslg:/mnt/wslg",
                "-e",
                "PULSE_SERVER",
                "-e",
                "SDL_AUDIODRIVER",
                "-e",
                "VOICEVOX_API_URL",
                "-e",
                "VOICEVOX_SPEAKER_ID",
                "your-local-docker-image-name"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {
                "PULSE_SERVER": "unix:/mnt/wslg/PulseServer",
                "SDL_AUDIODRIVER": "pulseaudio",
                "VOICEVOX_API_URL": "http://host.docker.internal:50031",
                "VOICEVOX_SPEAKER_ID": "919692871"
            },
            "args": [
                "/c",
                "docker",
                "run",
                "-i",
                "--rm",
                "-v",
                "/mnt/wslg:/mnt/wslg",
                "-e",
                "PULSE_SERVER",
                "-e",
                "SDL_AUDIODRIVER",
                "-e",
                "VOICEVOX_API_URL",
                "-e",
                "VOICEVOX_SPEAKER_ID",
                "your-local-docker-image-name"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {
                "PULSE_SERVER": "unix:/mnt/wslg/PulseServer",
                "SDL_AUDIODRIVER": "pulseaudio",
                "VOICEVOX_API_URL": "http://host.docker.internal:50031",
                "VOICEVOX_SPEAKER_ID": "919692871"
            },
            "args": [
                "/c",
                "docker",
                "run",
                "-i",
                "--rm",
                "-v",
                "/mnt/wslg:/mnt/wslg",
                "-e",
                "PULSE_SERVER",
                "-e",
                "SDL_AUDIODRIVER",
                "-e",
                "VOICEVOX_API_URL",
                "-e",
                "VOICEVOX_SPEAKER_ID",
                "your-local-docker-image-name"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "voicevox": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Macos

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Windows

{
    "env": {
        "PULSE_SERVER": "unix:/mnt/wslg/PulseServer",
        "SDL_AUDIODRIVER": "pulseaudio",
        "VOICEVOX_API_URL": "http://host.docker.internal:50031",
        "VOICEVOX_SPEAKER_ID": "919692871"
    },
    "args": [
        "/c",
        "docker",
        "run",
        "-i",
        "--rm",
        "-v",
        "/mnt/wslg:/mnt/wslg",
        "-e",
        "PULSE_SERVER",
        "-e",
        "SDL_AUDIODRIVER",
        "-e",
        "VOICEVOX_API_URL",
        "-e",
        "VOICEVOX_SPEAKER_ID",
        "your-local-docker-image-name"
    ],
    "command": "cmd"
}

Voicevox MCP Server

VOICEVOX互換の音声合成サーバー(AivisSpeech / VOICEVOX / COEIROINK) を MCP (Model Context Protocol) 経由で利用するためのサーバーです。 Cursor等でのClaude 3.7を使ったエージェントモードでの音声合成に利用できます。

必要条件

Windows環境

- Node.js 18以上 - VOICEVOX ENGINE等 (ローカルでhttp://localhost:50000等で実行) - VLCメディアプレーヤー（パスが通っていること）

Docker環境 (WSL2)

- Docker と Docker Compose - WSL2 - VOICEVOX ENGINE等 (ローカルまたはDockerで実行) - sudo apt install libsdl2-dev pulseaudio-utils pulseaudio されたLinux環境 - /mnt/wslg へのアクセス権限

インストールと設定

1. リポジトリをクローン ``


git clone https://github.com/Dosugamea/voicevox-mcp-server.git
cd voicevox-mcp-server



2. 依存関係のインストール


npm install



3. 環境変数の設定

.env_example をコピーして .env

 ファイルを作成し、必要に応じて設定を変更します:


VOICEVOX_API_URL=http://localhost:50021
VOICEVOX_SPEAKER_ID=1



実行方法


Windows環境での実行

エディタと別途で下記手順でサーバーを立ち上げてください。


npm run build
npm start



Docker環境での実行

エディタと別途での操作は不要です。
stdioモードで立ち上がるため直接実行することはできません。

設定方法


Windows環境での実行の場合

mcp.jsonに下記を追記してください。
接続が不安定なため切断されたら再接続してください。

json
        "voicevox": {
            "url": "http://localhost:10100/sse"
        }



Docker環境での実行の場合

mcp.jsonに下記を追記してください。
(作者環境での動作は確認できていません)

json
{
    "tools": {
        "voicevox": {
            "command": "cmd",
            "args": [
                "/c",
                "docker",
                "run",
                "-i",
                "--rm",
                "-v",
                "/mnt/wslg:/mnt/wslg",
                "-e",
                "PULSE_SERVER",
                "-e",
                "SDL_AUDIODRIVER",
                "-e",
                "VOICEVOX_API_URL",
                "-e",
                "VOICEVOX_SPEAKER_ID",
                "your-local-docker-image-name"
            ],
            "env": {
                "PULSE_SERVER": "unix:/mnt/wslg/PulseServer",
                "SDL_AUDIODRIVER": "pulseaudio",
                "VOICEVOX_API_URL": "http://host.docker.internal:50031",
                "VOICEVOX_SPEAKER_ID": "919692871"
            }
        }
    }
}



話者IDについて


話者IDは使用するVOICEVOXのモデルによって異なります。デフォルトでは「1」（四国めたん）を使用しています。
他の話者IDを使用する場合は、環境変数

VOICEVOX_SPEAKER_ID

 を変更してください。

話者IDの一覧は、VOICEVOX ENGINE APIの

/speakers

 エンドポイントで確認できます。
例:

curl http://localhost:50021/speakers`

トラブルシューティング

- VOICEVOXとの接続エラー: VOICEVOX ENGINEが起動していること、APIのURLが正しく設定されていることを確認してください。 - 音声が再生されない: VLCが正しくインストールされていることと、パスが通っていることを確認してください。 - Docker環境での音声出力問題: pulseaudioの設定が正しいか確認してください。

開発者向け情報

- ソースコードに貢献する場合は、Issueを作成するか、Pull Requestを送信してください。 - バグ報告や機能リクエストは、GitHubのIssue機能をご利用ください。

ライセンス

MIT License29:["$","div",null,{"className":"my-8 pb-8 h-full max-w-5xl mx-auto","children":["$","div",null,{"className":"grid grid-cols-1 md:grid-cols-3 gap-6","children":["$","$L30",null,{"mcp":{"id":"mcp_q96hHE3tvOXW","name":"VOICEVOX","description":"Connects AI systems to VOICEVOX text-to-speech engine for Japanese voice synthesis, supporting both default transport and Server-Sent Events with configurable speaker options.","logo":"https://avatars.githubusercontent.com/dosugamea","banner_url":null,"stars":3,"downloads":0,"categories":["design","ai","api","deployment","frontend","infrastructure"],"isRecommended":false,"created_at":"2025-04-17T01:24:46.925225+00:00","updated_at":"2025-04-17T01:47:39.601867+00:00","author":"dosugamea","average_rating":0,"total_ratings":0,"github_url":"https://github.com/dosugamea/voicevox-mcp-server","commit":"main","official":false,"bundler_compatible":false,"mcp_language":1,"slug":"dosugamea-voicevox","website":null,"is_sse":false,"summary":"Voicevox-MCP-Server is a TypeScript implementation that connects AI assistants to the VOICEVOX text-to-speech engine. Developed by Dosugamea, this server uses the mcp-framework to expose VOICEVOX's voice synthesis capabilities through a standardized interface. The implementation supports both default transport mechanisms and Server-Sent Events (SSE) for Wi

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

Claude Desktop / Cursor

Linux

Macos

Windows

Voicevox MCP Server

必要条件

Windows環境

Docker環境 (WSL2)

インストールと設定

実行方法

Windows環境での実行

Docker環境での実行

設定方法

Windows環境での実行の場合

Docker環境での実行の場合

話者IDについて

トラブルシューティング

開発者向け情報

ライセンス

Install

More like this

GitLab

Context 7

1Panel

🔎 GPT Researcher

Serena

FastMCP v2 🚀