Skip to main content
Glama
enesjakozh
hammeiam

Speech MCP Server

by hammeiam
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

音声MCPサーバー

Kokoro TTS モデルを使用してテキスト読み上げ機能を提供するモデル コンテキスト プロトコル サーバー。

構成

サーバーは次の環境変数を使用して構成できます。

変数

説明

デフォルト

有効範囲

MCP_DEFAULT_SPEECH_SPEED

テキスト読み上げのデフォルトの速度乗数

1.1

0.5から2.0

カーソル内:

{
  "mcpServers": {
    "speech": {
      "command": "npx",
      "args": [
        "-y",
        "speech-mcp-server"
      ],
      "env": {
        MCP_DEFAULT_SPEECH_SPEED: 1.3
      }
    }
  }
}

Related MCP server: TTS-MCP

特徴

  • 🎯 Kokoro TTS モデルを使用した高品質のテキスト読み上げ

  • 🗣️ 複数の音声オプションが利用可能

  • 🎛️ カスタマイズ可能な音声パラメータ（音声、速度）

  • 🔌 MCP準拠インターフェース

  • 📦 簡単なインストールとセットアップ

  • 🚀 APIキーは不要です

インストール

# Using npm
npm install speech-mcp-server

# Using pnpm (recommended)
pnpm add speech-mcp-server

# Using yarn
yarn add speech-mcp-server

使用法

サーバーを実行します。

# Using default configuration
npm start

# With custom speech speed
MCP_DEFAULT_SPEECH_SPEED=1.5 npm start

サーバーは次の MCP ツールを提供します。

  • text_to_speech : 基本的なテキスト読み上げ変換

  • text_to_speech_with_options : 速度をカスタマイズできるテキスト読み上げ

  • list_voices : 利用可能なすべての音声を一覧表示する

  • get_model_status : TTSモデルの初期化ステータスを確認する

発達

# Clone the repository
git clone <your-repo-url>
cd speech-mcp-server

# Install dependencies
pnpm install

# Start development server with auto-reload
pnpm dev

# Build the project
pnpm build

# Run linting
pnpm lint

# Format code
pnpm format

# Test with MCP Inspector
pnpm inspector

利用可能なツール

1. テキスト読み上げ

デフォルト設定を使用してテキストを音声に変換します。

{
  "type": "request",
  "id": "1",
  "method": "call_tool",
  "params": {
    "name": "text_to_speech",
    "arguments": {
      "text": "Hello world",
      "voice": "af_bella"  // optional
    }
  }
}

2. オプション付きテキスト読み上げ

カスタマイズ可能なパラメータを使用してテキストを音声に変換します。

{
  "type": "request",
  "id": "1",
  "method": "call_tool",
  "params": {
    "name": "text_to_speech_with_options",
    "arguments": {
      "text": "Hello world",
      "voice": "af_bella",  // optional
      "speed": 1.0,         // optional (0.5 to 2.0)
    }
  }
}

3. リストボイス

テキスト読み上げに使用できるすべての音声を一覧表示します。

{
  "type": "request",
  "id": "1",
  "method": "list_voices",
  "params": {}
}

4. get_model_status

TTSモデルの初期化の現在のステータスを確認します。モデルをダウンロードして初期化する必要があるため、サーバーの初回起動時に特に便利です。

{
  "type": "request",
  "id": "1",
  "method": "call_tool",
  "params": {
    "name": "get_model_status",
    "arguments": {}
  }
}

応答例:

{
  "content": [{
    "type": "text",
    "text": "Model status: initializing (5s elapsed)"
  }]
}

可能なステータス値:

  • uninitialized : モデルの初期化が開始されていません

  • initializing : モデルをダウンロードして初期化しています

  • ready : モデルは使用可能です

  • error : 初期化中にエラーが発生しました

テスト

MCP Inspector を使用するか、生の JSON メッセージを送信してサーバーをテストできます。

# List available tools
echo '{"type":"request","id":"1","method":"list_tools","params":{}}' | node dist/index.js

# List available voices
echo '{"type":"request","id":"2","method":"list_voices","params":{}}' | node dist/index.js

# Convert text to speech
echo '{"type":"request","id":"3","method":"call_tool","params":{"name":"text_to_speech","arguments":{"text":"Hello world","voice":"af_bella"}}}' | node dist/index.js

Claude Desktopとの統合

このサーバーを Claude Desktop で使用するには、Claude Desktop 構成ファイル ( ~/Library/Application Support/Claude/claude_desktop_config.json ) に次の行を追加します。

{
  "servers": {
    "speech": {
      "command": "npx",
      "args": ["@decodershq/speech-mcp-server"]
    }
  }
}

貢献

貢献を歓迎します！お気軽にプルリクエストを送信してください。

ライセンス

MIT ライセンス - 詳細についてはLICENSEファイルを参照してください。

トラブルシューティング

モデルの初期化の問題

サーバーは起動時に自動的にTTSモデルのダウンロードと初期化を試みます。初期化エラーが発生した場合は、以下の手順に従ってください。

  1. サーバーは、試行の間にクリーンアップを行いながら、最大3回まで自動的に再試行します。

  2. get_model_statusツールを使用して、初期化の進行状況とエラーを監視します。

  3. すべての再試行後も初期化が失敗した場合は、モデル ファイルを手動で削除してみてください。

# Remove model files (MacOS/Linux)
rm -rf ~/.npm/_npx/**/node_modules/@huggingface/transformers/.cache/onnx-community/Kokoro-82M-v1.0-ONNX/onnx/model_quantized.onnx
rm -rf ~/.cache/huggingface/transformers/onnx-community/Kokoro-82M-v1.0-ONNX/onnx/model_quantized.onnx

# Then restart the server
npm start

get_model_statusツールの応答に再試行情報が含まれるようになりました。

{
  "content": [{
    "type": "text",
    "text": "Model status: initializing (5s elapsed, retry 1/3)"
  }]
}

Available Tools

4 tools
get_model_statusB

Get the current status of the TTS model initialization

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves status, implying a read-only operation, but doesn't specify what the status includes (e.g., 'initialized', 'loading', 'error'), whether it has side effects, or how it handles errors. For a status-checking tool with zero annotation coverage, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that front-loads the core purpose without unnecessary details. It efficiently communicates the tool's function without redundancy or fluff, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no output schema, no annotations), the description is adequate but incomplete. It covers the basic purpose but lacks details on what the status output entails, error handling, or dependencies on other tools. For a status-checking tool, this leaves gaps in understanding its full context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately avoids discussing nonexistent inputs. A baseline of 4 is justified as the description doesn't introduce confusion about parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get') and resource ('current status of the TTS model initialization'), making the purpose immediately understandable. It distinguishes from siblings like list_voices and text_to_speech by focusing on model status rather than voice listing or speech generation. However, it doesn't explicitly differentiate from potential overlapping tools, keeping it at 4 rather than 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., whether the model must be initialized first), typical use cases (e.g., checking readiness before text_to_speech), or exclusions. This leaves the agent with minimal context for decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_voicesB

List all available voices for text-to-speech

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool lists voices but does not describe any behavioral traits such as rate limits, authentication needs, response format, or whether it's a read-only operation. This leaves significant gaps in understanding how the tool behaves beyond its basic function.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that directly states the tool's purpose without any unnecessary words or fluff. It is front-loaded and efficiently communicates the essential information, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (0 parameters, no output schema, no annotations), the description is minimally adequate. It states what the tool does but lacks details on behavioral aspects like response format or usage context. For a simple list tool, this is acceptable but leaves room for improvement in guiding the agent fully.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% coverage, so no parameter information is needed. The description appropriately does not discuss parameters, and since there are none, it meets the baseline expectation without requiring additional details, earning a score above the minimum.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List all available voices') and the resource ('for text-to-speech'), providing a specific verb+resource combination. However, it does not differentiate from sibling tools like 'get_model_status' or 'text_to_speech', which might also relate to voice or model operations, so it lacks explicit sibling distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving voice options but offers no explicit guidance on when to use this tool versus alternatives like 'text_to_speech' or 'get_model_status'. There is no mention of prerequisites, exclusions, or specific contexts, leaving the agent to infer usage from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

text_to_speechB

Convert text to speech and play it through system audio

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesThe text to convert to speech
voiceNoThe voice to use for speech synthesis (e.g. 'af_bella'). Use list_voices to see available options.

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the action and output ('play it through system audio'), but fails to address key traits like permissions needed, rate limits, whether it's a read-only or destructive operation, or error handling. This leaves significant gaps for an AI agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose without unnecessary details. Every word earns its place, making it highly concise and well-structured for quick understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a text-to-speech tool with no annotations and no output schema, the description is incomplete. It lacks information on behavioral aspects (e.g., audio format, playback behavior, errors) and does not explain return values or side effects, leaving the agent with insufficient context for reliable use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters (text and voice) thoroughly. The description does not add any additional meaning or context beyond what the schema provides, such as examples or usage notes for parameters. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('convert text to speech') and the resource ('system audio'), distinguishing it from siblings like list_voices (which lists options) and text_to_speech_with_options (which offers more customization). It uses precise verbs and specifies the output mechanism.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for converting text to audio playback, but does not explicitly state when to use this tool versus text_to_speech_with_options or other alternatives. It provides basic context but lacks explicit guidance on exclusions or comparisons with siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

text_to_speech_with_optionsC

Convert text to speech with customizable speed

ParametersJSON Schema
NameRequiredDescriptionDefault
textYesThe text to convert to speech
voiceNoThe voice to use for speech synthesis (e.g. 'af_bella'). Use list_voices to see available options.
speedNoSpeech rate multiplier (0.5 to 2.0)

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions 'customizable speed' but doesn't disclose other behavioral traits: it doesn't specify output format (e.g., audio file, stream), permissions required, rate limits, or whether it's a read-only or mutating operation. For a tool with no annotations, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without any fluff. It's appropriately sized and front-loaded, with every word earning its place. No structural issues or unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 parameters, no output schema, no annotations), the description is incomplete. It doesn't explain the output (e.g., what's returned, format), lacks behavioral context like error handling or performance, and doesn't guide usage relative to siblings. For a tool with no structured support, more descriptive detail is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters (text, voice, speed) thoroughly. The description adds minimal value beyond the schema—it implies speed customization but doesn't provide additional context like default values or examples. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: converting text to speech with customizable speed. It specifies the verb ('convert') and resource ('text to speech'), distinguishing it from siblings like list_voices (which lists options) or get_model_status (which checks status). However, it doesn't explicitly differentiate from text_to_speech (likely a simpler version), so it's not a perfect 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose text_to_speech_with_options over text_to_speech (the likely sibling), nor does it specify prerequisites like needing to list_voices first for voice selection. Usage is implied but not explicitly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 4 tool updates
    • First observedget_model_status
    • First observedlist_voices
    • First observedtext_to_speech
    • First observedtext_to_speech_with_options
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.4/5.0

Scored across 4 tools

Disambiguation4/5

The tools are mostly distinct, but 'text_to_speech' and 'text_to_speech_with_options' could cause confusion as they overlap in core functionality. The other tools ('get_model_status' and 'list_voices') have clear, unique purposes related to system status and voice selection.

Naming Consistency5/5

All tool names follow a consistent snake_case pattern with clear verb_noun structures (e.g., 'get_model_status', 'list_voices', 'text_to_speech'). There are no deviations in naming conventions across the set.

Tool Count4/5

Four tools is a reasonable count for a speech-focused server, though it feels slightly minimal. The tools cover key aspects like status, voice listing, and speech generation, but could potentially benefit from one or two more operations (e.g., stop speech or adjust volume) for better scope.

Completeness3/5

The server provides core text-to-speech functionality with status and voice listing, but lacks operations for managing speech playback (e.g., pause, stop, or volume control) and advanced customization beyond speed. This creates minor gaps that agents might need to work around for full speech interaction.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • TTS-MCP

    nakamurau1
    A
    license
    Not graded
    quality
    C
    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.
    7 npm
    1
    MIT

  • Edge-TTS MCP Server

    yuiseki
    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

Appeared in Searches