Skip to main content
Glama
ElevenLabs MCP Enhanced
by 199-mcp

ElevenLabs MCP Enhanced

npm version npm downloads Discord Community License

📑 Table of Contents

Related MCP server: ElevenLabs MCP Server

🚀 What's New in This Fork

This enhanced version adds critical conversational AI features missing from the original:

🤖 AI-Friendly Improvements (v1.0.0)

  • ✅ Official v3 API: Now uses official ElevenLabs endpoints - no proxy needed!

  • 🎯 Smart Voice Defaults: search_voices() now returns common working voices instantly

  • 📚 Educational Error Messages: Errors guide AI agents to success with examples

  • 💡 Clear Tool Guidance: No more confusion about single vs multi-speaker tools

  • 🎤 Accurate v3 Voice IDs: All 20 v3-optimized voices now have correct IDs and descriptions

  • 🏯 Auto-Split Long Dialogues: Automatically splits dialogues over 3000 chars into multiple files

  • 🎯 Auto-Adjust Stability: Invalid stability values auto-round to nearest valid option (0.0, 0.5, 1.0)

  • 🏷️ Smart Tag Simplification: Complex tags auto-convert to valid v3 tags for better quality

  • ⏱️ Dynamic Timeouts: Prevents timeouts on complex dialogues by calculating appropriate wait times

🆕 ElevenLabs v3 Model Support (Official)

  • 🎭 Enhanced Expressiveness: Use the official v3 model with model="v3" parameter

  • 🎤 Audio Tags: Add emotions and sound effects like [thoughtful], [crying], [laughing], [piano]

  • 👥 Multi-Speaker Dialogue: Generate natural conversations between multiple speakers

  • ✨ Dialogue Enhancement: Automatically enhance your dialogue with proper formatting and tags

  • 🌍 70+ Languages: v3 supports multilingual synthesis with emotional control

  • ✅ Official API: Now uses the official ElevenLabs text-to-dialogue endpoint

🎙️ Conversational AI Features

  • Conversation History: Retrieve full conversation details including transcripts

  • 📝 Transcript Access: Get conversation transcripts in multiple formats (plain, timestamps, JSON)

  • ⏳ Real-time Monitoring: Wait for ongoing conversations to complete and retrieve results

  • 🔍 Conversation Search: List and filter conversations by agent, status, and more

  • 🎨 Improved Formatting: Consistent formatting across all list operations

About

This is an enhanced fork of the official ElevenLabs Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech and audio processing APIs. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others to generate speech, clone voices, transcribe audio, manage conversational AI agents, and now retrieve conversation history.

🚀 Quick Install

No installation required! Just use npx:

npx elevenlabs-mcp-enhanced --api-key YOUR_API_KEY

Global Install

Install once, use everywhere:

npm install -g elevenlabs-mcp-enhanced
elevenlabs-mcp-enhanced --api-key YOUR_API_KEY

Environment Variable

Set your API key once:

export ELEVENLABS_API_KEY="your-api-key"
npx elevenlabs-mcp-enhanced

📋 Requirements

  • Node.js 16+ (for npm/npx)

  • Python 3.11+ (automatically managed by the npm package)

  • ElevenLabs API Key - Get one at elevenlabs.io

Quickstart with Claude Desktop

  1. Get your API key from ElevenLabs. There is a free tier with 10k credits per month.

  2. Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json to include the following:

{
  "mcpServers": {
    "ElevenLabs": {
      "command": "npx",
      "args": ["elevenlabs-mcp-enhanced"],
      "env": {
        "ELEVENLABS_API_KEY": "<insert-your-api-key-here>"
      }
    }
  }
}

That's it! No installation needed - npx will automatically download and run the server.

Option 2: Using Python (Original method)

If you prefer the original Python installation:

  1. Get your API key from ElevenLabs.

  2. Install from GitHub:

    pip install git+https://github.com/199-biotechnologies/elevenlabs-mcp-enhanced.git
  3. Configure Claude Desktop with:

    {
      "mcpServers": {
        "ElevenLabs": {
          "command": "python",
          "args": ["-m", "elevenlabs_mcp"],
          "env": {
            "ELEVENLABS_API_KEY": "<insert-your-api-key-here>"
          }
        }
      }
    }

If you're using Windows, you will have to enable "Developer Mode" in Claude Desktop to use the MCP server. Click "Help" in the hamburger menu at the top left and select "Enable Developer Mode".

Other MCP clients

Using npm/npx:

For other clients like Cursor and Windsurf, you can run the server directly:

npx elevenlabs-mcp-enhanced --api-key YOUR_API_KEY

Using Python:

  1. pip install elevenlabs-mcp

  2. python -m elevenlabs_mcp --api-key={{PUT_YOUR_API_KEY_HERE}} --print to get the configuration. Paste it into appropriate configuration directory specified by your MCP client.

That's it. Your MCP client can now interact with ElevenLabs through these tools:

Example usage

⚠️ Warning: ElevenLabs credits are needed to use these tools.

Try asking Claude:

  • "Create an AI agent that speaks like a film noir detective and can answer questions about classic movies"

  • "Generate three voice variations for a wise, ancient dragon character, then I will choose my favorite voice to add to my voice library"

  • "Convert this recording of my voice to sound like a medieval knight"

  • "Create a soundscape of a thunderstorm in a dense jungle with animals reacting to the weather"

  • "Turn this speech into text, identify different speakers, then convert it back using unique voices for each person"

🆕 v3 Model - Quick Start Guide

🎯 DECISION TREE:

  1. Single speaker? → Use text_to_speech with model="v3"

  2. Multiple speakers? → Use text_to_dialogue (automatically v3)

  3. Need tag examples? → Call fetch_v3_tags() first

📋 RECOMMENDED WORKFLOW FOR AI:

1. User: "Create an emotional story with sound effects"
2. AI: fetch_v3_tags() → Gets list of available tags
3. AI: search_voices("v3") → Gets v3-optimized voices
4. AI: text_to_dialogue(...) → Creates the story

Single Speaker Examples (text_to_speech):

  • "Generate: '[thoughtful] The universe is vast... [piano] ...and full of mysteries.'"

  • "Create narration with: '[whispering] Secret message [footsteps] [door creaking]'"

Multi-Speaker Examples (text_to_dialogue - ALWAYS v3):

# Simple conversation
inputs = [
    {"text": "How are you?", "voice_name": "James"},
    {"text": "I'm great!", "voice_name": "Jane"}
]

# With emotion tags
inputs = [
    {"text": "[excited] I found treasure!", "voice_name": "James"},
    {"text": "[skeptical] Really? [pause] Where?", "voice_name": "Jane"}
]

⚠️ v3 Requirements:

  • Stability: MUST be 0.0, 0.5, or 1.0 (no other values!)

  • Best voices: James, Jane, Sarah, Mark, etc. (search "v3" to find them)

  • Always check fetch_v3_tags() for available audio tags

🆕 New Conversation Features

With the enhanced conversation tools, you can now:

  • "Get the conversation transcript from conversation ID abc123" (automatically waits for completion)

  • "List all conversations from my agent and show me the completed ones"

  • "Get conversation xyz789 immediately without waiting" (set wait_for_completion=false)

  • "Show me all conversations in JSON format with timestamps"

  • "Get the conversation history including analysis data"

Note: The get_conversation tool now waits for conversations to complete by default (up to 5 minutes), ensuring you always get the full transcript.

Optional features

You can add the ELEVENLABS_MCP_BASE_PATH environment variable to the claude_desktop_config.json to specify the base path MCP server should look for and output files specified with relative paths.

✅ v3 Model - Now Officially Available!

The v3 model is now officially available through the ElevenLabs API! No proxy or special access needed - just use your regular API key.

What's New:

  • Official eleven_v3 model ID

  • Text-to-dialogue endpoint at /v1/text-to-dialogue

  • 70+ language support

  • 3,000 character limit per request

  • Enhanced emotional expressiveness

Usage: Simply set model="v3" in text_to_speech() or use text_to_dialogue() for multi-speaker content. The server now uses the official API endpoints.

Contributing

If you want to contribute or run from source:

  1. Clone the repository:

git clone https://github.com/elevenlabs/elevenlabs-mcp
cd elevenlabs-mcp
  1. Create a virtual environment and install dependencies using uv:

uv venv
source .venv/bin/activate
uv pip install -e ".[dev]"
  1. Copy .env.example to .env and add your ElevenLabs API key:

cp .env.example .env
# Edit .env and add your API key
  1. Run the tests to make sure everything is working:

./scripts/test.sh
# Or with options
./scripts/test.sh --verbose --fail-fast
  1. Install the server in Claude Desktop: mcp install elevenlabs_mcp/server.py

  2. Debug and test locally with MCP Inspector: mcp dev elevenlabs_mcp/server.py

Troubleshooting

Logs when running with Claude Desktop can be found at:

  • Windows: %APPDATA%\Claude\logs\mcp-server-elevenlabs.log

  • macOS: ~/Library/Logs/Claude/mcp-server-elevenlabs.log

Timeouts when using certain tools

Certain ElevenLabs API operations, like voice design and audio isolation, can take a long time to resolve. When using the MCP inspector in dev mode, you might get timeout errors despite the tool completing its intended task.

This shouldn't occur when using a client like Claude.

MCP ElevenLabs: spawn uvx ENOENT

If you encounter the error "MCP ElevenLabs: spawn uvx ENOENT", confirm its absolute path by running this command in your terminal:

which uvx

Once you obtain the absolute path (e.g., /usr/local/bin/uvx), update your configuration to use that path (e.g., "command": "/usr/local/bin/uvx"). This ensures that the correct executable is referenced.

Credits

Enhanced Fork

  • Boris Djordjevic - Lead Developer

  • 199 Longevity Team - Development and Testing

Original ElevenLabs MCP Server

This enhanced fork builds upon the excellent foundation created by the ElevenLabs team, adding critical conversational AI features for improved agent interaction and monitoring.

License

This project maintains the same MIT license as the original ElevenLabs MCP server. See LICENSE for details.

Available Tools

29 tools
add_knowledge_base_to_agentB

Adds knowledge to agent. Returns: knowledge base ID. Use when: giving agent access to documents or information.

Inputs: agent_id (required), knowledge_base_name (required), url, input_file_path, +1 more.

check_subscriptionA

Checks account subscription. Returns: subscription details and usage. Use when: monitoring API usage and limits.

Inputs: no named parameters.

create_agentB

Creates conversational AI agent. Returns: agent ID and details. Use when: setting up voice-enabled chatbot or assistant.

Inputs: name (required), first_message (required), system_prompt (required), voice_id, +13 more.

create_voice_from_previewB

Saves generated voice to library. Returns: permanent voice ID. Use when: keeping voice from text_to_voice previews.

Inputs: generated_voice_id (required), voice_name (required), voice_description (required).

enhance_dialogueB

Adds audio tags to dialogue. Returns: enhanced text with v3 tags. Use when: improving dialogue with emotions and effects.

Inputs: dialogue_blocks (required).

fetch_v3_tagsA

Lists v3 audio tags. Returns: comprehensive tag list. Use when: preparing text for text_to_speech_v3 or text_to_dialogue with emotions and effects.

Inputs: no named parameters.

get_agentB

Gets agent details. Returns: agent configuration. Use when: viewing specific agent settings and capabilities.

Inputs: agent_id (required).

get_conversationB

Gets conversation with transcript. Returns: conversation details and full transcript. Use when: analyzing completed agent conversations.

Inputs: conversation_id (required), wait_for_completion, include_analysis.

get_conversation_transcriptB

Gets conversation transcript in chunks. Returns: transcript chunk with metadata. Use when: retrieving large conversation transcripts.

Inputs: conversation_id (required), format, chunk, chunk_size.

get_v3_audio_tags_guideA

Gets v3 tag usage guide. Returns: detailed v3 documentation. Use when: learning how to use v3 audio tags effectively.

Inputs: no named parameters.

get_voiceB

Gets voice details. Returns: voice metadata and settings. Use when: need detailed information about a specific voice.

Inputs: voice_id (required).

get_voice_id_by_nameA

Resolves voice name to ID. Returns: JSON with voice_id and confidence. Use when: need voice ID from name with fuzzy matching.

Inputs: voice_name (required).

isolate_audioA

Removes background noise from audio. Returns: cleaned audio file path. Use when: extracting voice from noisy recordings.

Inputs: input_file_path (required), output_directory.

list_agentsB

Lists all agents. Returns: agent list with IDs. Use when: viewing available conversational AI agents.

Inputs: no named parameters.

list_conversationsB

Lists agent conversations. Returns: conversation list with metadata. Use when: browsing conversation history.

Inputs: agent_id, status, limit, offset.

list_modelsA

Lists available TTS models. Returns: model list with capabilities. Use when: choosing between v2, v3, or other models.

Inputs: no named parameters.

list_phone_numbersA

Lists account phone numbers. Returns: phone number list. Use when: viewing available numbers for outbound calls.

Inputs: no named parameters.

make_outbound_callB

Initiates phone call with agent. Returns: call details. Use when: making automated calls via Twilio integration.

Inputs: agent_id (required), agent_phone_number_id (required), to_number (required).

play_audioA

Plays audio file locally. Returns: playback confirmation. Use when: previewing generated audio without downloading.

Inputs: input_file_path (required).

search_voice_libraryB

Searches global voice library. Returns: shared voices list. Use when: finding voices across entire ElevenLabs platform.

Inputs: page, page_size, search.

search_voicesB

Searches available voices. Returns: JSON with voice details. Use when: finding voices by name, gender, or characteristics.

Inputs: search, sort, sort_direction, return_format.

speech_to_speechB

Transforms voice in audio. Returns: audio file with new voice. Use when: changing speaker voice in existing audio.

Inputs: input_file_path (required), voice_name, output_directory.

speech_to_textC

Transcribes audio to text. Returns: transcript text or file path. Use when: converting speech recordings to text.

Inputs: input_file_path (required), language_code, diarize, save_transcript_to_file, +2 more.

text_to_dialogueB

Converts multi-speaker text to audio. Returns: dialogue audio file paths. Use when: creating conversations with multiple voices.

Inputs: inputs (required), output_directory, stability, similarity_boost.

text_to_sound_effectsC

Generates sound effects from text. Returns: audio file path. Use when: creating custom sound effects from descriptions.

Inputs: text (required), duration_seconds, output_directory, output_format.

text_to_speechC

Converts text to speech (v2/v3/flash models). Returns: audio file path. Use when: single speaker narration. Supports v3 with audio tags.

Inputs: text (required), voice_name, output_directory, voice_id, +8 more.

text_to_speech_v3A

Converts text to speech with v3 model and tags. Returns: audio file path. Use when: single speaker needs emotions, pauses, or sound effects.

Inputs: text (required), voice_name, output_directory, voice_id, +2 more.

text_to_voiceA

Creates voice from description. Returns: three voice preview files. Use when: designing custom voice from text prompt.

Inputs: voice_description (required), text, output_directory.

voice_cloneB

Creates voice clone from audio. Returns: new voice ID. Use when: creating custom voice from recordings.

Inputs: name (required), files (required), description.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.3/5.0

    Scored across 29 tools

    Disambiguation3/5

    Most tools have distinct purposes, but there is notable overlap between text_to_speech and text_to_speech_v3, which could cause confusion as both handle single-speaker narration with v3 support mentioned in text_to_speech. Additionally, get_conversation and get_conversation_transcript serve similar functions with minor differences in output format, potentially leading to misselection. However, descriptions help clarify boundaries in most cases.

    Naming Consistency4/5

    Tool names follow a consistent snake_case pattern throughout, with clear verb_noun structures (e.g., create_agent, list_models, get_voice). Minor deviations exist, such as text_to_speech_v3 including a version suffix, but this is reasonable for differentiation. Overall, the naming is predictable and readable, supporting easy identification.

    Tool Count3/5

    With 29 tools, the count is borderline high for the ElevenLabs domain, which covers voice generation, agents, and audio processing. While the scope is broad, some tools might be consolidated (e.g., overlapping speech functions), making it feel slightly heavy. However, it's not extreme and remains manageable for the apparent feature set.

    Completeness5/5

    The tool set provides comprehensive coverage for the ElevenLabs domain, including CRUD operations for agents and voices, audio processing (speech-to-text, isolation), generation (text-to-speech, dialogue, sound effects), and utilities (subscription, playback). There are no obvious gaps; agents can handle full workflows from creation to conversation analysis, and voice management includes cloning, searching, and previewing.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers