Kokoro TTS MCP Server
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
Primero, instale el administrador de paquetes
uv:
curl -LsSf https://astral.sh/uv/install.sh | shClonar 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 vozvoice(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 audioplay_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 toolgenerate_speechD
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| voice | No | af_heart | |
| speed | No | ||
| save_path | No | ||
| play_audio | No |
TDQS
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.
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.
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.
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.
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.
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 tool update
v0.2.0- First observed
generate_speech
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion. The tool's purpose is clearly distinct.
The single tool name 'generate_speech' follows a clear verb_noun pattern, which is consistent and descriptive.
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.
A single tool for TTS lacks coverage for common operations like listing voices, configuring parameters, or stopping generation, leading to significant gaps.
Maintenance
Related MCP Connectors
- AudexumOAuthcom.audexum
Text to speech and transcription for any AI model: MP3 voiceovers, audio and YouTube to text.
1 Text to speech for your AI. Your AI can send text to Doc Player to read it aloud. You will see a reader window with the text and you can control the playback sentence by sentence. Find an example here: https://documentplayer.com/connect-ai/
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
AI voice generation: text-to-speech and voice cloning from any MCP client.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides text-to-speech capabilities using the Kokoro TTS model, offering multiple voice options and customizable speech parameters.422 npm2MIT
- FlicenseBqualityBmaintenanceEnables seamless integration with Typecast API through the Model Context Protocol, allowing clients to manage voices, convert text to speech, and play audio in a standardized way.113-
- AlicenseAqualityDmaintenanceA Model Context Protocol server that enables AI models to generate and play high-quality text-to-speech audio through your device's native audio system using Rime's voice synthesis API.158 npm27-
- AlicenseBqualityDmaintenanceA 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.28MIT