Skip to main content
Glama

Escarcha MCP

escarcha

Un servidor de Protocolo de Contexto de Modelo (MCP) que proporciona funciones de conversión de texto a voz mediante la API de Rime. Este servidor descarga audio y lo reproduce mediante el reproductor de audio nativo del sistema.

Características

  • Expone una herramienta speak que convierte texto en voz y lo reproduce a través del audio del sistema.

  • Utiliza la API de síntesis de voz de alta calidad de Rime

Related MCP server: AivisSpeech MCP Server

Requisitos

  • Node.js 16.x o superior

  • Un dispositivo de salida de audio que funcione

  • macOS: utiliza afplay

Hay un código de muestra de Claude para lo siguiente que no está probado 🤙✨

  • Windows: Media.SoundPlayer integrado (PowerShell)

  • Linux: mpg123, mplayer, aplay o ffplay

Configuración de MCP

"ref": {
  "command": "npx",
  "args": ["rime-mcp"],
  "env": {
      RIME_API_KEY=your_api_key_here

      # Optional configuration
      RIME_GUIDANCE="<guide how the agent speaks>"
      RIME_WHO_TO_ADDRESS="<your name>"
      RIME_WHEN_TO_SPEAK="<tell the agent when to speak>"
      RIME_VOICE="cove" 
  }
}

Todas las variables de entorno opcionales son parte de la definición de la herramienta y son indicaciones para

Aquí se enumeran todas las opciones de voz.

Puede obtener su clave API desde el panel de control de Rime .

Las siguientes variables de entorno se pueden utilizar para personalizar el comportamiento:

  • RIME_GUIDANCE : La descripción principal de cuándo y cómo utilizar la herramienta de voz

  • RIME_WHO_TO_ADDRESS : A quién debe dirigirse el discurso (predeterminado: "usuario")

  • RIME_WHEN_TO_SPEAK : Cuándo se debe utilizar la herramienta (predeterminado: "cuando se le pide que hable o al finalizar un comando")

  • RIME_VOICE : La voz predeterminada a utilizar (predeterminada: "cove")

Ejemplos de casos de uso

Demostración de Rime MCP en Cursor

Ejemplo 1: Anuncios del agente de codificación

"RIME_WHEN_TO_SPEAK": "Always conclude your answers by speaking.",
"RIME_GUIDANCE": "Give a brief overview of the answer. If any files were edited, list them."

Ejemplo 2: Aprende cómo hablan los niños hoy en día

RIME_GUIDANCE="Use phrases and slang common among Gen Alpha."
RIME_WHO_TO_ADDRESS="Matt"
RIME_WHEN_TO_SPEAK="when asked to speak"

Ejemplo 3: Diferentes idiomas según el contexto

RIME_VOICE="use 'cove' when talking about Typescript and 'antoine' when talking about Python"

Desarrollo

  1. Instalar dependencias:

npm install
  1. Construir el servidor:

npm run build
  1. Ejecutar en modo de desarrollo con recarga en caliente:

npm run dev

Licencia

Instituto Tecnológico de Massachusetts (MIT)

Available Tools

1 tool
speakA

Speak text aloud using Rime's text-to-speech API. Should be used when user asks you to speak or to announce and explain when you finish a command

User configuration:

WHO_TO_ADDRESS: user

WHEN_TO_SPEAK: when asked to speak or when finishing a command

VOICE: cove

GUIDANCE: Use the speak tool to convert text to speech when the user requests audio output or when providing verbal responses

Inputs: text (required), speaker, speedAlpha, reduceLatency.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or overlap between tools. The speak tool has a single, clearly defined purpose for text-to-speech conversion.

    Naming Consistency5/5

    A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'speak' follows a clear verb pattern appropriate for its function.

    Tool Count2/5

    A single tool is too few for most MCP server purposes, even for a text-to-speech service. This feels thin and limited, lacking complementary tools like volume control, voice selection, or speech status checks that would enhance functionality.

    Completeness2/5

    The tool surface is severely incomplete for a text-to-speech domain. While the speak tool covers the core output function, there are obvious gaps such as no tools for managing voices, adjusting speech parameters, stopping speech, or checking speech status, which limits agent capabilities.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    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
      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