ElevenLabs MCP Server
Servidor MCP de ElevenLabs
Un servidor de Protocolo de Contexto de Modelo (MCP) que se integra con la API de texto a voz de ElevenLabs, que incluye un componente de servidor y un cliente MCP basado en web de muestra (SvelteKit) para gestionar tareas de generación de voz.
Características
Generar audio a partir de texto usando la API de ElevenLabs
Soporte para múltiples voces y partes del guión
Base de datos SQLite para almacenamiento de historial persistente
Cliente MCP de SvelteKit de muestra para:
Conversión sencilla de texto a voz
Gestión de guiones de varias partes
Seguimiento y reproducción del historial de voz
Descargas de archivos de audio
Related MCP server: ElevenLabs MCP Server
Instalación
Instalación mediante herrería
Para instalar ElevenLabs MCP Server para Claude Desktop automáticamente a través de Smithery :
npx -y @smithery/cli install elevenlabs-mcp-server --client claudeUso de uvx (recomendado)
Al utilizar uvx , no se necesita ninguna instalación específica.
Agregue la siguiente configuración a su archivo de configuración de MCP (por ejemplo, cline_mcp_settings.json para Claude Desktop):
{
"mcpServers": {
"elevenlabs": {
"command": "uvx",
"args": ["elevenlabs-mcp-server"],
"env": {
"ELEVENLABS_API_KEY": "your-api-key",
"ELEVENLABS_VOICE_ID": "your-voice-id",
"ELEVENLABS_MODEL_ID": "eleven_flash_v2",
"ELEVENLABS_STABILITY": "0.5",
"ELEVENLABS_SIMILARITY_BOOST": "0.75",
"ELEVENLABS_STYLE": "0.1",
"ELEVENLABS_OUTPUT_DIR": "output"
}
}
}
}Instalación de desarrollo
Clonar este repositorio
Instalar dependencias:
uv venvCopie
.env.examplea.envy complete sus credenciales de ElevenLabs
{
"mcpServers": {
"elevenlabs": {
"command": "uv",
"args": [
"--directory",
"path/to/elevenlabs-mcp-server",
"run",
"elevenlabs-mcp-server"
],
"env": {
"ELEVENLABS_API_KEY": "your-api-key",
"ELEVENLABS_VOICE_ID": "your-voice-id",
"ELEVENLABS_MODEL_ID": "eleven_flash_v2",
"ELEVENLABS_STABILITY": "0.5",
"ELEVENLABS_SIMILARITY_BOOST": "0.75",
"ELEVENLABS_STYLE": "0.1",
"ELEVENLABS_OUTPUT_DIR": "output"
}
}
}
}Uso del cliente MCP de muestra de SvelteKit
Navegue hasta el directorio de la interfaz web:
cd clients/web-uiInstalar dependencias:
pnpm installCopie
.env.examplea.envy configúrelo según sea necesarioEjecute la interfaz web:
pnpm devAbra http://localhost:5174 en su navegador
Herramientas disponibles
generate_audio_simple: Genera audio a partir de texto simple usando la configuración de voz predeterminadagenerate_audio_script: Genera audio a partir de un guión estructurado con múltiples voces y actoresdelete_job: Eliminar un trabajo por su IDget_audio_file: Obtener el archivo de audio por su IDlist_voices: Lista todas las voces disponiblesget_voiceover_history: Obtiene el historial de trabajos de locución. Opcionalmente, especifique un ID de trabajo para un trabajo específico.
Recursos disponibles
voiceover://history/{job_id}: Obtener el archivo de audio por su IDvoiceover://voices: Lista todas las voces disponibles
Licencia
Este proyecto está licenciado bajo la licencia MIT: consulte el archivo de LICENCIA para obtener más detalles.
Available Tools
6 toolsdelete_jobB
Delete a voiceover job and its associated files
Inputs: job_id (required).
generate_audio_scriptB
Generate audio from a structured script with multiple voices and actors. Accepts either: 1. Plain text string 2. JSON string with format: { "script": [ { "text": "Text to speak", "voice_id": "optional-voice-id", "actor": "optional-actor-name" }, ... ] }
Inputs: script (required).
generate_audio_simpleC
Generate audio from plain text using default voice settings
Inputs: text (required), voice_id.
get_audio_fileC
Get the audio file content for a specific job
Inputs: job_id (required).
get_voiceover_historyB
Get voiceover job history. Optionally specify a job ID for a specific job.
Inputs: job_id.
list_voicesB
Get a list of all available ElevenLabs voices with metadata
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no ambiguity. delete_job removes jobs, generate_audio_script creates multi-voice audio from structured input, generate_audio_simple creates basic audio, get_audio_file retrieves audio content, get_voiceover_history accesses job history, and list_voices lists available voices. The two generation tools are clearly differentiated by complexity level.
All tools follow a consistent verb_noun pattern throughout: delete_job, generate_audio_script, generate_audio_simple, get_audio_file, get_voiceover_history, list_voices. The naming convention is perfectly uniform with clear action-object relationships and no mixing of styles.
Six tools is an ideal number for this audio generation domain. It provides complete coverage of core workflows (generation, retrieval, management, discovery) without being overwhelming. Each tool earns its place with clear utility in the voiceover job lifecycle.
The toolset provides complete CRUD/lifecycle coverage for ElevenLabs voiceover operations: create (two generation tools), read (get_audio_file, get_voiceover_history, list_voices), delete (delete_job). There are no obvious gaps - agents can create audio, retrieve results, manage jobs, and discover available voices.
Maintenance
Related MCP Connectors
ElevenLabs in natural language: generate speech in any language, create and manage voices, compose m
Manage ElevenLabs voice agents and generate speech, music, sound effects, images, and video.
Text to speech, voice listing and phrase library search for AI assistants. API key header.
Text to speech in 200+ languages, voice cloning, voice design and SRT captions.
Related MCP Servers
- AlicenseAqualityNot gradedmaintenanceEnables interaction with ElevenLabs Text-to-Speech and audio processing APIs. Supports speech generation, voice cloning, audio transcription, and sound effect creation through natural language.24MIT
- AlicenseAqualityFmaintenanceEnables text-to-speech conversion using ElevenLabs API with voice management, streaming support, and multiple models.517 PyPI1MIT
- AlicenseAqualityDmaintenanceEnables streaming text-to-speech generation using ElevenLabs with real-time audio playback and voice listing.2MIT
- FlicenseNot gradedqualityDmaintenanceProvides tools for generating speech from text using the ElevenLabs API, including voice listing, text-to-speech conversion, and quota checking.-
Appeared in Searches
- Automating Workflow for File Processing and Communication
- A workflow for processing and sharing meeting-related materials
- A platform providing TTS (Text-to-Speech) capabilities
- Talking to Claude desktop in Russian using map-server connection
- A Minecraft client for regular internet users, not developers or experts