Skip to main content
Glama
AivisSpeech MCP Server

AivisSpeech MCP Server

by kentaro

AivisSpeech MCP Server

This is an implementation of the Model Context Protocol (MCP) server for AivisSpeech. This server works with the AivisSpeech Engine to provide an interface for speech synthesis. Through the MCP protocol, it becomes easy to use AivisSpeech's speech synthesis function from applications such as AI assistants.

overview

AivisSpeech MCP Server provides the following features:

  • MCP protocol compliant API endpoints

  • High-quality voice synthesis in cooperation with AivisSpeech Engine

  • Type-safe design with TypeScript

  • Easy to configure and highly scalable architecture

Related MCP server: TTS-MCP

Prerequisites

  • Node.js 18.x or higher

  • npm 9.x or higher

  • AivisSpeech Engine (requires separate installation)

install

# リポジトリをクローン
git clone https://github.com/kentaro/aivis-speech-mcp.git
cd aivis-speech-mcp

# 依存関係のインストール
npm install

# ビルド
npm run build

# 環境変数の設定
cp .env.sample .env
# .envファイルを編集して、必要な設定を行ってください

# Cursor MCPの設定
cp .cursor/mcp.json.sample .cursor/mcp.json
# mcp.jsonファイル内の"/path/to/aivis-speech-mcp/dist/index.js"を
# 実際のプロジェクトパスに書き換えてください
# 例: "C:/Users/username/path/to/aivis-speech-mcp/dist/index.js"

Environment settings

In your .env file, set the following:

# AivisSpeech API Configuration
AIVIS_SPEECH_API_URL=http://localhost:10101  # AivisSpeech EngineのAPIエンドポイント

# Speaker Configuration
AIVIS_SPEECH_SPEAKER_ID=888753760  # デフォルトのスピーカーID

Cursor MCP Settings

In .cursor/mcp.json file, configure the following:

{
  "mcpServers": {
    "AivisSpeech-MCP": {
      "command": "node",
      "args": ["/path/to/aivis-speech-mcp/dist/index.js"]
    }
  }
}

Replace /path/to/aivis-speech-mcp/dist/index.js with the path to your project. For Windows, escape the backslashes or use forward slashes. For example: "C:/Users/username/path/to/aivis-speech-mcp/dist/index.js"

How to use

Development Mode

During development you can start the server with hot reloading with the following command:

npm run dev

Build

To build for production run the following command:

npm run build

Production Mode

After building, start the server in production mode with the following command:

npm start

test

To run the tests use the following command:

npm test

architecture

AivisSpeech MCP Server consists of the following components:

  • MCP Service : Provides a server that complies with the Model Context Protocol and processes requests from clients.

  • AivisSpeech Service : Communicates with the AivisSpeech Engine API and performs speech synthesis.

API Specifications

We provide API endpoints that comply with the MCP protocol. The main features are as follows:

  • Speech synthesis (generating speech from text)

  • Get speaker information

  • Audio style settings

For detailed API specifications, please refer to AivisSpeech Engine API Specification .

Integration with MCP protocol

This server implements the Model Context Protocol (MCP) and can be used seamlessly with applications such as AI assistants. For more information about the MCP protocol, see the official MCP documentation .

troubleshooting

Common issues and solutions:

  • Can't connect to AivisSpeech Engine : Check if AIVIS_SPEECH_API_URL in .env file is set correctly

  • No sound : Check your system's audio settings and make sure the correct audio device is selected

  • Speaker ID not found : Make sure AivisSpeech Engine is running properly and check for available speaker IDs.

contribution

Please report bugs and feature requests via our GitHub issue tracker. Pull requests are also welcome.

license

MIT

Acknowledgements

Available Tools

1 tool
aivis-speech-synthesisD

Inputs: text (required), intonation_scale, output_sampling_rate, pitch_scale, +6 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    D1.7/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'aivis-speech-synthesis' stands alone with a distinct purpose, so agents cannot misselect among multiple options.

    Naming Consistency5/5

    A single tool inherently has consistent naming, as there are no other tools to compare it against. The name 'aivis-speech-synthesis' follows a clear pattern of domain-specific naming, and no inconsistencies can arise from a set of one.

    Tool Count2/5

    A single tool for a speech synthesis server is too few for typical use cases, as it lacks essential operations like configuration, status checks, or batch processing. This minimal scope limits functionality and suggests an incomplete or overly simplistic implementation for the domain.

    Completeness1/5

    The tool set is severely incomplete for a speech synthesis domain, offering only synthesis without any supporting operations like listing voices, adjusting parameters, checking synthesis status, or handling errors. This creates significant gaps that will likely cause agent failures in real-world scenarios.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that integrates high-quality text-to-speech capabilities with Claude Desktop and other MCP-compatible clients, supporting multiple voice options and audio formats.
      1
      MIT
    • A
      license
      B
      quality
      F
      maintenance
      A server that enables Claude 3.7 and other AI agents to access VOICEVOX-compatible speech synthesis engines (AivisSpeech, VOICEVOX, COEIROINK) through the Model Context Protocol.
      1
      12
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that provides text-to-speech functionality for AI agents using Microsoft Edge's text-to-speech technology, supporting multiple voices, languages, and voice customization.
      2
      8
      MIT