ElevenLabs

by docker ✓ verified ✓ Packaged by Docker

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

MCP server installable needs setup network: on runtime: sysbox

AI & LLM MCP Servers

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

Attribute	Details
Docker Image	mcp/elevenlabs
Author	elevenlabs
Repository	https://github.com/elevenlabs/elevenlabs-mcp

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	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 provided by this Server	Short Description
`add_knowledge_base_to_agent`	Add a knowledge base to ElevenLabs workspace.
`check_subscription`	Check the current subscription status.
`compose_music`	Convert a prompt to music and save the output audio file to a given directory.
`create_agent`	Create a conversational AI agent with custom configuration.
`create_composition_plan`	Create a composition plan for music generation.
`create_voice_from_preview`	Add a generated voice to the voice library.
`get_agent`	Get details about a specific conversational AI agent
`get_conversation`	Gets conversation with transcript.
`get_voice`	Get details of a specific voice
`isolate_audio`	Isolate audio from a file.
`list_agents`	List all available conversational AI agents
`list_conversations`	Lists agent conversations.
`list_models`	List all available models
`list_phone_numbers`	List all phone numbers associated with the ElevenLabs account
`make_outbound_call`	Make an outbound call using an ElevenLabs agent.
`play_audio`	Play an audio file.
`search_voice_library`	Search for a voice across the entire ElevenLabs voice library.
`search_voices`	Search for existing voices, a voice that has already been added to the user's ElevenLabs voice library.
`simulate_conversation`	Simulate a text conversation between a conversational AI agent and a simulated user.
`speech_to_speech`	Transform audio from one voice to another using provided audio files.
`speech_to_text`	Transcribe speech from an audio file.
`text_to_sound_effects`	Convert text description of a sound effect to sound effect with a given duration.
`text_to_speech`	Convert text to speech with a given voice.
`text_to_voice`	Create voice previews from a text prompt.
`upload_music_for_inpainting`	Upload an existing audio file to ElevenLabs so it can be referenced in music_v2 inpainting workflows.
`video_to_music`	Generate background music for one or more video files.
`voice_clone`	Create an instant voice clone of a voice using provided audio files.

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.

Parameters	Type	Description
`agent_id`	`string`	ID of the agent to add the knowledge base to.
`knowledge_base_name`	`string`	Name of the knowledge base.
`input_file_path`	`string` optional	Path to the file to add to the knowledge base.
`text`	`string` optional	Text to add to the knowledge base.
`url`	`string` optional	URL of the knowledge base.

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.

Parameters	Type	Description
`composition_plan`	`string` optional	Composition plan dict. Shape depends on model_id (see above). Must provide either prompt or composition_plan.
`force_instrumental`	`boolean` optional	If True, the model will avoid generating lyrics/vocals.
`model_id`	`string` optional	Which music model to use. One of "music_v1" or "music_v2". Defaults to "music_v2".
`music_length_ms`	`string` optional	Length of the generated music in milliseconds (3000-600000). Cannot be used if composition_plan is provided.
`output_directory`	`string` optional	Directory to save the output audio file
`prompt`	`string` optional	Prompt to convert to music. Must provide either prompt or composition_plan.
`seed`	`string` optional	Optional integer seed for reproducible generation (music_v2 only).
`store_for_inpainting`	`boolean` optional	If True, the generated song is stored server-side and the returned song_id can be used in later inpainting calls (as an AudioRefChunk.song_id, or conditioning_ref).

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.

Parameters	Type	Description
`first_message`	`string`	First message the agent will say i.e. "Hi, how can I help you today?"
`name`	`string`	Name of the agent
`system_prompt`	`string`	System prompt for the agent
`asr_quality`	`string` optional	Quality of the ASR. `high` or `low`.
`language`	`string` optional	ISO 639-1 language code for the agent
`llm`	`string` optional	LLM to use for the agent
`max_duration_seconds`	`integer` optional	Maximum duration of a conversation in seconds. Defaults to 600 seconds (10 minutes).
`max_tokens`	`string` optional	Maximum number of tokens to generate.
`model_id`	`string` optional	ID of the ElevenLabs model to use for the agent.
`optimize_streaming_latency`	`integer` optional	Optimize streaming latency. Range is 0 to 4.
`record_voice`	`boolean` optional	Whether to record the agent's voice.
`retention_days`	`integer` optional	Number of days to retain the agent's data.
`similarity_boost`	`number` optional	Similarity boost for the agent. Range is 0 to 1.
`stability`	`number` optional	Stability for the agent. Range is 0 to 1.
`temperature`	`number` optional	Temperature for the agent. The lower the temperature, the more deterministic the agent's responses will be. Range is 0 to 1.
`turn_timeout`	`integer` optional	Timeout for the agent to respond in seconds. Defaults to 7 seconds.
`voice_id`	`string` optional	ID of the voice to use for the agent

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": [...]}`.

Parameters	Type	Description
`prompt`	`string`	Prompt to create a composition plan for
`model_id`	`string` optional	Which music model to plan for. One of "music_v1" or "music_v2". Defaults to "music_v2".
`music_length_ms`	`string` optional	The length of the composition plan to generate in milliseconds. Must be between 10000ms and 300000ms. Optional - if not provided, the model will choose a length based on the prompt.
`source_composition_plan`	`string` optional	An optional composition plan dict to use as a source for the new composition plan. Should match the shape of the model_id you request.

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.

Parameters	Type	Description
`generated_voice_id`	`string`
`voice_description`	`string`
`voice_name`	`string`

This tool interacts with external entities.

Tool: `get_agent`

Get details about a specific conversational AI agent

Parameters	Type	Description
`agent_id`	`string`

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.

Parameters	Type	Description
`conversation_id`	`string`	The unique identifier of the conversation to retrieve, you can get the ids from the list_conversations tool.

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

Parameters	Type	Description
`voice_id`	`string`

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.

Parameters	Type	Description
`input_file_path`	`string`
`output_directory`	`string` optional

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.

Parameters	Type	Description
`agent_id`	`string` optional
`call_start_after_unix`	`string` optional
`call_start_before_unix`	`string` optional
`cursor`	`string` optional
`max_length`	`integer` optional
`page_size`	`integer` optional

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.

Parameters	Type	Description
`agent_id`	`string`	The ID of the agent that will handle the call
`agent_phone_number_id`	`string`	The ID of the phone number to use for the call
`to_number`	`string`	The phone number to call (E.164 format: +1xxxxxxxxxx)

This tool may perform destructive updates.

This tool interacts with external entities.

Tool: `play_audio`

Play an audio file. Supports WAV and MP3 formats.

Parameters	Type	Description
`input_file_path`	`string`

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.

Parameters	Type	Description
`page`	`integer` optional	Page number to return (0-indexed)
`page_size`	`integer` optional	Number of voices to return per page (1-100)
`search`	`string` optional	Search term to filter voices by

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.

Parameters	Type	Description
`search`	`string` optional	Search term to filter voices by. Searches in name, description, labels and category.
`sort`	`string` optional	Which field to sort by. `created_at_unix` might not be available for older voices.
`sort_direction`	`string` optional	Sort order, either ascending or descending.

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.

Parameters	Type	Description
`agent_id`	`string`	ID of the agent to test. Use list_agents to find IDs.
`simulated_user_prompt`	`string`	Instructions for how the simulated user should behave.
`extra_evaluation_criteria`	`string` optional	Optional list of dicts, each with:
`first_message`	`string` optional	Optional opening message to kick off the conversation.
`max_turns`	`integer` optional	Maximum conversation turns. Defaults to 10.

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.

Parameters	Type	Description
`input_file_path`	`string`
`output_directory`	`string` optional
`voice_name`	`string` optional

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.

Parameters	Type	Description
`input_file_path`	`string`
`diarize`	`boolean` optional	Whether to diarize the audio file. If True, which speaker is currently speaking will be annotated in the transcription.
`language_code`	`string` optional	ISO 639-3 language code for transcription. If not provided, the language will be detected automatically.
`output_directory`	`string` optional	Directory where files should be saved (only used when saving files).
`return_transcript_to_client_directly`	`boolean` optional	Whether to return the transcript to the client directly.
`save_transcript_to_file`	`boolean` optional	Whether to save the transcript to a file.

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.

Parameters	Type	Description
`text`	`string`	Text description of the sound effect
`duration_seconds`	`number` optional	Duration of the sound effect in seconds
`loop`	`boolean` optional	Whether to loop the sound effect. Defaults to False.
`output_directory`	`string` optional	Directory where files should be saved (only used when saving files).
`output_format`	`string` optional

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.

Parameters	Type	Description
`text`	`string`
`language`	`string` optional	ISO 639-1 language code for the voice.
`model_id`	`string` optional
`output_directory`	`string` optional
`output_format`	`string` optional
`similarity_boost`	`number` optional
`speed`	`number` optional
`stability`	`number` optional
`style`	`number` optional
`use_speaker_boost`	`boolean` optional
`voice_id`	`string` optional
`voice_name`	`string` optional

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.

Parameters	Type	Description
`voice_description`	`string`
`output_directory`	`string` optional
`text`	`string` optional

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.

Parameters	Type	Description
`input_file_path`	`string`	Path to a local audio file to upload.
`extract_composition_plan`	`string` optional	Which model to extract a composition plan for ("music_v1" or "music_v2"). Pass None to skip extraction. Defaults to "music_v2".

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.

Parameters	Type	Description
`input_file_paths`	`array`	Paths to the video files. Order is preserved.
`description`	`string` optional	Optional natural-language direction for the music (e.g. "Build suspense, then resolve with a warm cinematic finish.").
`model_id`	`string` optional	Which music model to use. One of "music_v1" or "music_v2". Defaults to "music_v2".
`output_directory`	`string` optional	Directory to save the generated audio file. Defaults to $HOME/Desktop.
`tags`	`string` optional	Optional list of up to 10 short style cues (e.g. ["cinematic", "suspenseful", "uplifting"]).

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.

Parameters	Type	Description
`files`	`array`
`name`	`string`
`description`	`string` optional

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?

Install

Open LabStore on any connected Selfmade Ninja Labs instance and press Get — or run this from the instance shell:

labsctl store-install mcp-elevenlabs

About

Kind: MCP server
Publisher: docker
Version: 7cd8be5396ee
Updated: 13 Oct 2026
Transport: stdio
Licence: MIT License
Owner: elevenlabs
Packaged by: Docker

Secrets needed

ELEVENLABS_API_KEY: elevenlabs.api_key

Tools (27)

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 whic
check_subscription: Check the current subscription status. Could be used to measure the usage of the API.
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 $HOM
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
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. Composi
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 whi
get_agent: Get details about a specific conversational AI agent
get_conversation: Gets conversation with transcript. Returns: conversation details and full transcript. Use when: analyzing completed agent conversations.
get_voice: Get details of a specific voice
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 in
list_agents: List all available conversational AI agents
list_conversations: Lists agent conversations. Returns: conversation list with metadata. Use when: asked about conversation history.
list_models: List all available models
list_phone_numbers: List all phone numbers associated with the ElevenLabs account
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: T
play_audio: Play an audio file. Supports WAV and MP3 formats.
search_voice_library: Search for a voice across the entire ElevenLabs voice library.
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.
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.
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 m
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_clie
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
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
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 tex
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 A
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
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

Source

View upstream ↗

View repository ↗

image mcp/elevenlabs@sha256:ad57886f6a7bc33538e6cb71aa79b063592e56b910994c50495ab891d1cd364c

digest sha256:ad57886f6a7bc33538e…

Every store app is stripped of privileged/host-mount settings at install and runs contained on the installing host. The rules.

ElevenLabs MCP Server

MCP Info

Image Building Info

Available Tools (27)

Tools Details

Tool: add_knowledge_base_to_agent

Tool: check_subscription

Tool: compose_music

Tool: create_agent

Tool: create_composition_plan

Tool: create_voice_from_preview

Tool: get_agent

Tool: get_conversation

Tool: get_voice

Tool: isolate_audio

Tool: list_agents

Tool: list_conversations

Tool: list_models

Tool: list_phone_numbers

Tool: make_outbound_call

Tool: play_audio

Tool: search_voice_library

Tool: search_voices

Tool: simulate_conversation

Tool: speech_to_speech

Tool: speech_to_text

Tool: text_to_sound_effects

Tool: text_to_speech

Tool: text_to_voice

Tool: upload_music_for_inpainting

Tool: video_to_music

Tool: voice_clone

Use this MCP Server

Tool: `add_knowledge_base_to_agent`

Tool: `check_subscription`

Tool: `compose_music`

Tool: `create_agent`

Tool: `create_composition_plan`

Tool: `create_voice_from_preview`

Tool: `get_agent`

Tool: `get_conversation`

Tool: `get_voice`

Tool: `isolate_audio`

Tool: `list_agents`

Tool: `list_conversations`

Tool: `list_models`

Tool: `list_phone_numbers`

Tool: `make_outbound_call`

Tool: `play_audio`

Tool: `search_voice_library`

Tool: `search_voices`

Tool: `simulate_conversation`

Tool: `speech_to_speech`

Tool: `speech_to_text`

Tool: `text_to_sound_effects`

Tool: `text_to_speech`

Tool: `text_to_voice`

Tool: `upload_music_for_inpainting`

Tool: `video_to_music`

Tool: `voice_clone`