ElevenLabs MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ELEVENLABS_API_KEY | Yes | Your ElevenLabs API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| elevenlabs_text_to_speechC | Convert text to speech using ElevenLabs API |
| elevenlabs_list_voicesA | Get all available voices from your ElevenLabs account |
| elevenlabs_get_voice_infoC | Get detailed information about a specific voice |
| elevenlabs_stream_text_to_speechA | Convert text to speech with streaming (for longer texts or real-time generation) |
| elevenlabs_get_modelsA | Get all available text-to-speech models |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
The tools are mostly distinct: listing voices, getting voice details, getting models, and generating speech. The potential confusion between stream_text_to_speech and text_to_speech is mitigated by the description clarifying the streaming use case, but they still share the same core function.
The naming follows a consistent elevenlabs_ prefix with verb_noun structure for most tools (list_voices, get_voice_info, get_models, stream_text_to_speech). However, 'text_to_speech' deviates as it lacks an explicit verb, making it slightly inconsistent.
Five tools is well-scoped for a text-to-speech MCP server, covering voice exploration, model lookup, and two TTS generation modes. Each tool serves a clear purpose within the domain.
The tool set covers the essential operations: listing and retrieving voice details, listing models, and generating speech (both standard and streaming). Minor gaps exist such as voice management (create/update/delete) but they are not core to the primary TTS workflow.