ElevenLabs MCP Server
by mamertofabian
The ElevenLabs MCP Server integrates with the ElevenLabs text-to-speech API, providing a server component and a sample web-based MCP Client for managing voice generation tasks. It allows users to generate audio from text using ElevenLabs' voices and manage script parts.
Last updated: N/A
What is ElevenLabs MCP Server?
The ElevenLabs MCP Server is a Model Context Protocol server that acts as an interface to the ElevenLabs text-to-speech API. It includes a server component and a sample SvelteKit-based web client for managing and executing text-to-speech tasks.
How to use ElevenLabs MCP Server?
To use the server, you can install it via Smithery or manually using uvx. Configure the server with your ElevenLabs API key and desired voice settings. The sample SvelteKit client provides a web interface for interacting with the server, allowing you to generate audio from text, manage scripts, and track voiceover history.
Key features of ElevenLabs MCP Server
Generate audio from text using ElevenLabs API
Support for multiple voices and script parts
SQLite database for persistent history storage
Sample SvelteKit MCP Client for managing voice generation tasks
Voice history tracking and playback
Audio file downloads
Use cases of ElevenLabs MCP Server
Generating voiceovers for videos
Creating audio content for podcasts
Developing interactive voice applications
Automating text-to-speech workflows
FAQ from ElevenLabs MCP Server
What is MCP?
What is MCP?
MCP stands for Model Context Protocol. It's a protocol for interacting with models, in this case, the ElevenLabs text-to-speech API.
How do I get an ElevenLabs API key?
How do I get an ElevenLabs API key?
You need to sign up for an account on the ElevenLabs website and obtain an API key from your account settings.
What is the purpose of the SvelteKit client?
What is the purpose of the SvelteKit client?
The SvelteKit client provides a user-friendly web interface for interacting with the ElevenLabs MCP Server, making it easier to manage voice generation tasks.
Can I use different voices with this server?
Can I use different voices with this server?
Yes, the server supports using different voices available through the ElevenLabs API. You can specify the voice ID in the server configuration or through the client interface.
Where are the generated audio files stored?
Where are the generated audio files stored?
By default, the generated audio files are stored in the 'output' directory. This can be configured by setting the ELEVENLABS_OUTPUT_DIR environment variable.