Skip to main content
Glama
giannisanni

Kokoro TTS MCP Server

by giannisanni

Servidor MCP Kokoro TTS

Un servidor de Protocolo de Contexto de Modelo (MCP) que proporciona capacidades de conversión de texto a voz mediante el motor TTS de Kokoro. Este servidor expone la funcionalidad TTS mediante herramientas MCP, lo que facilita la integración de la síntesis de voz en sus aplicaciones.

Prerrequisitos

  • Python 3.10 o superior

  • administrador de paquetes uv

Related MCP server: Typecast API MCP Server

Instalación

  1. Primero, instale el administrador de paquetes uv :

curl -LsSf https://astral.sh/uv/install.sh | sh
  1. Clonar este repositorio e instalar las dependencias:

uv venv
source .venv/bin/activate  # On Windows, use: .venv\Scripts\activate
uv pip install .

Características

  • Síntesis de texto a voz con voces personalizables

  • Velocidad de voz ajustable

  • Soporte para guardar audio en archivos o reproducción directa

  • Compatibilidad con reproducción de audio multiplataforma (Windows, macOS, Linux)

Uso

El servidor proporciona una única herramienta MCP generate_speech con los siguientes parámetros:

  • text (obligatorio): El texto que se convertirá a voz

  • voice (opcional): Voz que se utilizará para la síntesis (predeterminado: "af_heart")

  • speed (opcional): Multiplicador de velocidad del habla (predeterminado: 1.0)

  • save_path (opcional): Directorio para guardar archivos de audio

  • play_audio (opcional): si se debe reproducir el audio inmediatamente (predeterminado: Falso)

Ejemplo de uso

from mcp.client import Client

async with Client() as client:
    await client.connect("kokoro-tts")
    
    # Generate and play speech
    result = await client.call_tool(
        "generate_speech",
        {
            "text": "Hello, world!",
            "voice": "af_heart",
            "speed": 1.0,
            "play_audio": True
        }
    )

Dependencias

  • kokoro >= 0.8.4

  • mcp[cli] >= 1.3.0

  • archivo de sonido >= 0.13.1

Soporte de plataforma

La reproducción de audio es compatible con:

  • Windows (usando start )

  • macOS (usando afplay )

  • Linux (usando aplay )

Configuración de MCP

Agregue la siguiente configuración a su archivo de configuración de MCP:

{
  "mcpServers": {
    "kokoro-tts": {
      "command": "/Users/giannisan/pinokio/bin/miniconda/bin/uv",
      "args": [
        "--directory",
        "/Users/giannisan/Documents/Cline/MCP/kokoro-tts-mcp",
        "run",
        "tts-mcp.py"
      ]
    }
  }
}

Licencia

[Agregue la información de su licencia aquí]

Available Tools

1 tool
generate_speechD
ParametersJSON Schema
NameRequiredDescriptionDefault
textYes
voiceNoaf_heart
speedNo
save_pathNo
play_audioNo

TDQS

D1/5.0
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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. 1 tool updatev0.2.0
    • First observedgenerate_speech

TDQS

D1.8/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion. The tool's purpose is clearly distinct.

Naming Consistency5/5

The single tool name 'generate_speech' follows a clear verb_noun pattern, which is consistent and descriptive.

Tool Count3/5

One tool for a TTS server is borderline; while it may suffice for basic functionality, it feels thin for a typical service that might include voice selection or other parameters.

Completeness2/5

A single tool for TTS lacks coverage for common operations like listing voices, configuring parameters, or stopping generation, leading to significant gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers