mcp/elevenlabs repository overview

⁠ElevenLabs MCP Server

Official ElevenLabs Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech and audio processing APIs.

What is an MCP Server?⁠

⁠MCP Info

⁠Image Building Info

Attribute	Details
Dockerfile	https://github.com/elevenlabs/elevenlabs-mcp/blob/afc22357432db9e8b33991a83d41906001f6d759/Dockerfile⁠
Commit	afc22357432db9e8b33991a83d41906001f6d759
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/elevenlabs --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub
Licence	MIT License

⁠Available Tools (27)

⁠Tools Details

⁠Tool: add_knowledge_base_to_agent

Add a knowledge base to ElevenLabs workspace. Allowed types are epub, pdf, docx, txt, html.

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool interacts with external entities.

⁠Tool: check_subscription

Check the current subscription status. Could be used to measure the usage of the API.

⁠Tool: compose_music

Convert a prompt to music and save the output audio file to a given directory. Directory is optional, if not provided, the output file will be saved to $HOME/Desktop. Saves output file to directory (default: $HOME/Desktop).

Two models are supported:
- music_v2 (default): latest model. Composition plans use a `chunks` array where each chunk is either a `GenerationChunk` (text, duration_ms, positive_styles, negative_styles, context_adherence, optional conditioning_ref + condition_strength) or an `AudioRefChunk` ({song_id, range: {start_ms, end_ms}}) for inpainting. Inpainting also requires the source song to have been stored — call this tool with store_for_inpainting=True or use upload_music_for_inpainting first to get a song_id.
- music_v1: legacy model. Composition plans use positive_global_styles, negative_global_styles, sections.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: create_agent

Create a conversational AI agent with custom configuration.

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool interacts with external entities.

⁠Tool: create_composition_plan

Create a composition plan for music generation. Usage of this endpoint does not cost any credits but is subject to rate limiting depending on your tier. Composition plans can be used when generating music with the compose_music tool.

The returned plan shape depends on model_id:
- music_v2 (default): `{"chunks": [GenerationChunk | AudioRefChunk, ...]}`. Each GenerationChunk has `text`, `duration_ms`, `positive_styles`, `negative_styles`, `context_adherence` and optional `conditioning_ref` + `condition_strength`. AudioRefChunks reference a stored song via `song_id` and `range: {start_ms, end_ms}` for inpainting.
- music_v1: `{"positive_global_styles": [...], "negative_global_styles": [...], "sections": [...]}`.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: create_voice_from_preview

Add a generated voice to the voice library. Uses the voice ID from the text_to_voice tool.

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool interacts with external entities.

⁠Tool: get_agent

Get details about a specific conversational AI agent

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: get_conversation

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

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: get_voice

Get details of a specific voice

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: isolate_audio

Isolate audio from a file. Saves output file to directory (default: $HOME/Desktop).

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: list_agents

List all available conversational AI agents

⁠Tool: list_conversations

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

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: list_models

List all available models

⁠Tool: list_phone_numbers

List all phone numbers associated with the ElevenLabs account

⁠Tool: make_outbound_call

Make an outbound call using an ElevenLabs agent. Automatically detects provider type (Twilio or SIP trunk) and uses the appropriate API.

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool may perform destructive updates.

This tool interacts with external entities.

⁠Tool: play_audio

Play an audio file. Supports WAV and MP3 formats.

This tool is read-only. It does not modify its environment.

⁠Tool: search_voice_library

Search for a voice across the entire ElevenLabs voice library.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: search_voices

Search for existing voices, a voice that has already been added to the user's ElevenLabs voice library. Searches in name, description, labels and category.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: simulate_conversation

Simulate a text conversation between a conversational AI agent and a simulated user. Runs the full conversation and returns the transcript plus analysis.

Use this to test agent behaviour, evaluate prompts, and catch failure modes without
a live call. The simulated user follows the persona you describe.

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs.
Only use when explicitly requested by the user.

This tool interacts with external entities.

⁠Tool: speech_to_speech

Transform audio from one voice to another using provided audio files. Saves output file to directory (default: $HOME/Desktop).

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: speech_to_text

Transcribe speech from an audio file. When save_transcript_to_file=True: Saves output file to directory (default: $HOME/Desktop). When return_transcript_to_client_directly=True, always returns text directly regardless of output mode.

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: text_to_sound_effects

Convert text description of a sound effect to sound effect with a given duration. Saves output file to directory (default: $HOME/Desktop).

Duration must be between 0.5 and 5 seconds.

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: text_to_speech

Convert text to speech with a given voice. Saves output file to directory (default: $HOME/Desktop).

Only one of voice_id or voice_name can be provided. If none are provided, the default voice will be used.

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: text_to_voice

Create voice previews from a text prompt. Creates three previews with slight variations. Saves output file to directory (default: $HOME/Desktop).

If no text is provided, the tool will auto-generate text.

Voice preview files are saved as: voice_design_(generated_voice_id)_(timestamp).mp3

Example file name: voice_design_Ya2J5uIa5Pq14DNPsbC1_20250403_164949.mp3

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: upload_music_for_inpainting

Upload an existing audio file to ElevenLabs so it can be referenced in music_v2 inpainting workflows. Returns a song_id you can plug into a composition plan's AudioRefChunks (or a generation chunk's conditioning_ref) to edit or extend the track via the compose_music tool.

Optionally extracts a composition plan from the uploaded audio so you have a starting point to mutate.

Note: this endpoint is gated to enterprise customers with inpainting access.

This tool interacts with external entities.

⁠Tool: video_to_music

Generate background music for one or more video files. Saves output file to directory (default: $HOME/Desktop).

The videos are concatenated server-side in the order provided; the generated score targets the combined duration. Constraints: 1-10 videos per call, combined size <= 200 MB, combined duration <= 600 seconds.

This tool is read-only. It does not modify its environment.

This tool interacts with external entities.

⁠Tool: voice_clone

Create an instant voice clone of a voice using provided audio files.

⚠️ COST WARNING: This tool makes an API call to ElevenLabs which may incur costs. Only use when explicitly requested by the user.

This tool interacts with external entities.

⁠Use this MCP Server

{
  "mcpServers": {
    "elevenlabs": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "ELEVENLABS_API_KEY",
        "-v",
        "/local-directory:/local-directory",
        "mcp/elevenlabs"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "<ELEVENLABS_API_KEY>"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠