Skip to main content
Glama
Sign In
ElevenLabs Streaming MCP Server

ElevenLabs Streaming MCP Server

by CodingButter
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

ElevenLabs Streaming MCP Server

A high-performance MCP (Model Context Protocol) server for ElevenLabs text-to-speech with streaming support!

Features

  • ✅ Official ElevenLabs SDK integration

  • ✅ True streaming - no file saving!

  • ✅ Direct pipe to ffplay for instant playback

  • ✅ No token limit issues

  • ✅ Environment-based configuration

  • ✅ Voice listing support

  • ✅ Works with npx - no installation needed!

Related MCP server: ElevenLabs MCP Server

Quick Start

Add to your .mccp.json:

{
  "mcpServers": {
    "elevenlabs": {
      "command": "npx",
      "args": ["elevenlabs-streaming-mcp-server"],
      "env": {
        "ELEVENLABS_API_KEY": "your_api_key_here",
        "ELEVENLABS_VOICE_ID": "Au8OOcCmvsCaQpmULvvQ",
        "ELEVENLABS_MODEL_ID": "eleven_flash_v2",
        "ELEVENLABS_STABILITY": "0.5",
        "ELEVENLABS_SIMILARITY_BOOST": "0.75",
        "ELEVENLABS_STYLE": "0.1"
      }
    }
  }
}

Environment Variables

  • ELEVENLABS_API_KEY (required): Your ElevenLabs API key

  • ELEVENLABS_VOICE_ID: Default voice ID (default: Rusty Butter's voice)

  • ELEVENLABS_MODEL_ID: Model to use (default: eleven_flash_v2)

  • ELEVENLABS_STABILITY: Voice stability 0-1 (default: 0.5)

  • ELEVENLABS_SIMILARITY_BOOST: Voice similarity 0-1 (default: 0.75)

  • ELEVENLABS_STYLE: Style exaggeration 0-1 (default: 0.1)

Available Tools

generate_audio

Generates audio from text with streaming support:

  • text (required): Text to convert to speech

  • voice_id: Override default voice

  • model_id: Override default model

  • play_audio: Whether to auto-play (default: true)

list_voices

Lists all available ElevenLabs voices with their IDs and descriptions.

Development

npm install
npm run dev   # Run with hot reload
npm run build # Build for production

Publishing

npm publish

Built by Rusty Butter for MAXIMUM STREAMING AUTONOMY! 🚀

Available Tools

2 tools
generate_audioB

Generate and stream audio from text using ElevenLabs

Inputs: text (required), model_id, voice_id, play_audio.

list_voicesA

List available ElevenLabs voices

Inputs: no named parameters.

Tool Schema Changelog

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

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.6/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have entirely distinct purposes: generate_audio creates audio from text, while list_voices retrieves available voices. There is no overlap or ambiguity between them.

    Naming Consistency5/5

    Both tool names follow a clear verb_noun pattern (generate_audio, list_voices), demonstrating consistent and predictable naming.

    Tool Count3/5

    With only two tools, the set feels thin for a general-purpose MCP server, though it may be acceptable for a focused streaming service. The count is on the low end of the appropriate range.

    Completeness3/5

    The tools cover the core generation and voice discovery workflow, but lack voice management (create/update/delete) and more granular streaming controls. There are minor gaps that could force workarounds in more complex scenarios.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers