ElevenLabs

ElevenLabs MCP Connector for Claude

A+

Generate lifelike speech, clone voices, and create sound effects using ElevenLabs' industry-leading AI audio technology.

34 tools Official Updated Oct 1, 2026 Official Vinkius Partner

Connect your ElevenLabs account to any AI agent to generate high-quality audio, manage voices, and process sound directly through natural conversation.

What you can do

  • Text-to-Speech — Convert text into lifelike speech using a wide array of pre-made or custom voices with granular control over stability and similarity.
  • Voice Management — List, retrieve, edit, and delete voices in your library. You can even design new voices or find similar ones.
  • Speech-to-Speech — Transform audio from one voice to another while maintaining emotion and delivery.
  • Audio Processing — Isolate audio to remove background noise and create clean voice tracks.
  • Sound Effects — Generate unique sound effects from text descriptions for games, videos, or presentations.
  • Project & Dubbing — Manage long-form projects and create automated dubbing workflows across multiple languages.

How it works

  1. Subscribe to this server
  2. Enter your ElevenLabs API Key
  3. Start generating and managing audio from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Content Creators — instantly generate voiceovers for videos and social media without leaving your workflow.
  • Developers — integrate high-quality audio synthesis into applications and test voice settings via the AI agent.
  • Sound Designers — quickly prototype sound effects and clean up audio recordings using AI-powered isolation.
text-to-speechvoice-cloninggenerative-audiospeech-synthesisai-voiceaudio-processing

34 tools expose this connector's capabilities to your AI agent.

stream_isolate_audio

Stream audio isolation

isolate_audio

Remove background noise from audio

create_agent

Supply a name and the required conversation configuration. Create a Conversational AI agent

create_designed_voice

Save a designed voice

create_dub

Create a dubbing project

create_single_use_token

Create a single-use token

create_speech

Convert text to speech

delete_history_item

Ensure the history item ID is correct. Delete a history item

design_voice

Design a new voice from a prompt

find_similar_voices

Find similar voices in the library

generate_sound

Generate sound effects from text

get_dub_status

Use the specific dubbing ID for the query. Get status of a dubbing project

get_history_item

Provide a valid history item ID. Get details of a history item

get_user

Get user info and subscription details

list_dictionaries

List pronunciation dictionaries

list_dubs

List dubbing projects

list_history

Get generated items history

list_projects

Provide project details to list them. List Studio projects

list_voices

List available voices

stream_convert_speech

Stream Voice Changer (Speech to Speech)

stream_speech

Stream text to speech

convert_speech

Voice Changer (Speech to Speech)

list_models

). List available models

list_agents

List Conversational AI agents

add_dictionary_from_file

The file_base64 parameter is required for the operation. Add pronunciation dictionary from a PLS file

add_dictionary_from_rules

Provide the rules array if the dictionary name is omitted. Add pronunciation dictionary from rules

create_project

Provide a name; default voice IDs are optional. Create a Studio project

delete_voice

Ensure the voice ID is correct before proceeding with deletion. Delete a custom voice

edit_voice

You must provide both a voice ID and a name. Edit a custom voice

get_character_stats

Get character usage statistics

get_history_audio

Use the specific history item ID. Download audio for a history item

get_snapshot

Supply the project ID and snapshot ID. Get a project snapshot

get_voice

Provide a valid voice ID to retrieve information. Get details for a specific voice

list_agent_branches

Supply the agent’s unique ID. List branches for a Conversational AI agent

See how to talk to your AI agent using ElevenLabs.

List all available voices in my ElevenLabs library.

I've retrieved your voices. You have 12 voices available, including 'Rachel' (ID: 21m00Tcm4TlvDq8ikWAM) and 'Clyde' (ID: 2EiwWnXFnvU5JabPnv8n). Would you like to use one of these for speech generation?

Generate a sound effect of a futuristic laser blast.

Generating sound effect... I've created a 'futuristic laser blast' audio. You can now download or play the generated sound effect.

Convert this text to speech using voice ID pNInz6obpgmqMArWsc7r: 'The future of audio is here.'

Processing text-to-speech... I've generated the audio for your text using the specified voice. The high-quality speech file is ready.

You can use the `create_speech` tool. Simply provide the `voice_id` and the `text` you want to synthesize. The agent will generate the audio for you.

Related Connectors