Skip to main content
Glama
Say MCP Server

Say MCP Server

by bmorphism

decir-servidor-mcp

Configuración de voz del sistema macOS

Un servidor MCP que proporciona funcionalidad de conversión de texto a voz mediante el comando say integrado de macOS.

Requisitos

  • macOS (usa el comando say integrado)

  • Node.js >= 14.0.0

Related MCP server: mcp-speak

Configuración

Agregue lo siguiente a su archivo de configuración de MCP:

{
  "mcpServers": {
    "say": {
      "command": "node",
      "args": ["/path/to/say-mcp-server/build/index.js"]
    }
  }
}

Instalación

npm install say-mcp-server

Herramientas

hablar

La herramienta speak proporciona acceso a las capacidades de texto a voz de macOS con amplias opciones de personalización.

Uso básico

Utilice la función de texto a voz de macOS para decir texto en voz alta.

Parámetros:

  • text (obligatorio): Texto para hablar. Compatible con:

    • Texto sin formato

    • Puntuación básica para pausas

    • Nuevas líneas para cortes naturales

    • [[slnc 500]] para un silencio de 500 ms

    • [[rate 200]] para cambiar la velocidad a mitad del texto

    • [[volm 0.5]] para cambiar el volumen a mitad del texto

    • [[emph +]] y [[emph -]] para enfatizar

    • [[pbas +10]] para ajuste de tono

  • voice (opcional): Voz a utilizar (predeterminada: "Alex")

  • rate (opcional): velocidad de habla en palabras por minuto (predeterminado: 175, rango: 1-500)

  • background (opcional): ejecuta el discurso en segundo plano para permitir una mayor interacción con MCP (predeterminado: falso)

Funciones avanzadas

  1. Modulación de voz:

use_mcp_tool({
  server_name: "say",
  tool_name: "speak",
  arguments: {
    text: "[[volm 0.7]] This is quieter [[volm 1.0]] and this is normal [[volm 1.5]] and this is louder",
    voice: "Victoria"
  }
});
  1. Cambios dinámicos de velocidad:

use_mcp_tool({
  server_name: "say",
  tool_name: "speak",
  arguments: {
    text: "Normal speed [[rate 300]] now speaking faster [[rate 100]] and now slower",
    voice: "Fred"
  }
});
  1. Énfasis y tono:

use_mcp_tool({
  server_name: "say",
  tool_name: "speak",
  arguments: {
    text: "[[emph +]] Important point! [[emph -]] [[pbas +10]] Higher pitch [[pbas -10]] Lower pitch",
    voice: "Samantha"
  }
});

Ejemplos de integración

  1. Con Marginalia Buscar:

// Search for a topic and have the results read aloud
const searchResult = await use_mcp_tool({
  server_name: "marginalia-mcp-server",
  tool_name: "search",
  arguments: { query: "quantum computing basics", count: 1 }
});

await use_mcp_tool({
  server_name: "say",
  tool_name: "speak",
  arguments: {
    text: searchResult.results[0].description,
    voice: "Daniel",
    rate: 150
  }
});
  1. Con transcripciones de YouTube:

// Read a YouTube video transcript
const transcript = await use_mcp_tool({
  server_name: "youtube-transcript",
  tool_name: "get_transcript",
  arguments: {
    url: "https://youtube.com/watch?v=example",
    lang: "en"
  }
});

await use_mcp_tool({
  server_name: "say",
  tool_name: "speak",
  arguments: {
    text: transcript.text,
    voice: "Samantha",
    rate: 175
  }
});
  1. Discurso de fondo con múltiples acciones:

// Start long speech in background
await use_mcp_tool({
  server_name: "say",
  tool_name: "speak",
  arguments: {
    text: "This is a long speech that will run in the background...",
    voice: "Rocko (Italian (Italy))",
    rate: 69,
    background: true
  }
});

// Immediately perform another action while speech continues
await use_mcp_tool({
  server_name: "marginalia-mcp-server",
  tool_name: "search",
  arguments: { query: "parallel processing" }
});
  1. Con Apple Notes:

// Read notes aloud
const notes = await use_mcp_tool({
  server_name: "apple-notes-mcp",
  tool_name: "search-notes",
  arguments: { query: "meeting notes" }
});

if (notes.length > 0) {
  await use_mcp_tool({
    server_name: "say",
    tool_name: "speak",
    arguments: {
      text: notes[0].content,
      voice: "Karen",
      rate: 160
    }
  });
}

Ejemplo:

use_mcp_tool({
  server_name: "say",
  tool_name: "speak",
  arguments: {
    text: "Hello, world!",
    voice: "Victoria",
    rate: 200
  }
});

lista_voces

Enumere todas las voces de texto a voz disponibles en el sistema.

Ejemplo:

use_mcp_tool({
  server_name: "say",
  tool_name: "list_voices",
  arguments: {}
});

Voces recomendadas

Configuración

Agregue lo siguiente a su archivo de configuración de MCP:

{
  "mcpServers": {
    "say": {
      "command": "node",
      "args": ["/path/to/say-mcp-server/build/index.js"]
    }
  }
}

Requisitos

  • macOS (usa el comando say integrado)

  • Node.js >= 14.0.0

Colaboradores

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

2 tools
list_voicesB

List available text-to-speech voices

Inputs: no named parameters.

speakA

Use macOS text-to-speech to speak text aloud

Inputs: text (required), background, rate, voice.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: list_voices retrieves available options, while speak performs the core text-to-speech action. There is no overlap or ambiguity between them, making it easy for an agent to select the correct tool.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun pattern (list_voices and speak), with clear, descriptive names that align with their functions. There are no deviations or mixed conventions in the naming style.

    Tool Count2/5

    With only two tools, the server feels thin for a text-to-speech domain. While it covers basic functionality (listing and speaking), it lacks operations like stopping speech, adjusting voice parameters, or managing speech queues, which are common in such systems.

    Completeness2/5

    The tool surface is severely incomplete for a text-to-speech server. It provides list and speak functions but misses essential operations such as pausing, resuming, or canceling speech, and offers no control over voice settings like rate or volume, limiting agent workflows.

    Maintenance

    ActivityInactive
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers