ElevenLabs

@mindstone/mcp-server-elevenlabs

ElevenLabs MCP server for Model Context Protocol hosts. Generate speech, music, and sound effects, browse voices, and transcribe audio using the ElevenLabs API through a standardised MCP interface.

Status

• Version: 0.5.2 · npm
• Auth: API key (ELEVENLABS_API_KEY)
• Tools: 32 (account, usage, voices, speech, music, transcription, voice conversion, isolation, alignment, cloning, dialogue, voice design, dubbing, history, pronunciation dictionaries)
• Surface: cloud-api
• Machine-readable: STATUS.json

Requirements

• Node.js 20+
• npm

One-click install

After clicking the button, your host will prompt you to fill: ELEVENLABS_API_KEY.

Manual config for Claude Desktop / Claude Code / Goose / Continue.dev (ElevenLabs)

{

"mcpServers": { "ElevenLabs": { "command": "npx", "args": [ "-y", "@mindstone/mcp-server-elevenlabs" ], "env": { "ELEVENLABS_API_KEY": "" } } } }

Quick Start

Install & build

cd <path-to-repo>/connectors/elevenlabs

npm install npm run build

npx (once published)

npx -y @mindstone/mcp-server-elevenlabs

Local

node dist/index.js

Configuration

Environment variables

• ELEVENLABS_API_KEY — ElevenLabs API key (starts with sk_)
• MCP_HOST_BRIDGE_STATE — optional path to a host bridge state file used for credential management
• MINDSTONE_REBEL_BRIDGE_STATE — backwards-compatible alias for MCP_HOST_BRIDGE_STATE

Host configuration examples

Claude Desktop / Cursor

{

"mcpServers": { "ElevenLabs": { "command": "npx", "args": ["-y", "@mindstone/mcp-server-elevenlabs"], "env": { "ELEVENLABS_API_KEY": "your-api-key" } } } }

Local development (no npm publish needed)

{

"mcpServers": { "ElevenLabs": { "command": "node", "args": [" /connectors/elevenlabs/dist/index.js"], "env": { "ELEVENLABS_API_KEY": "your-api-key" } } } }

Tools (32)

Configuration

• configure_elevenlabs_api_key — Save your ElevenLabs API key

Account & discovery (FREE)

• check_subscription — Check subscription tier and character credit usage
• get_usage_stats — Credit usage over time grouped by product/model/voice (workspace analytics API)
• list_models — List TTS models with languages and capabilities

Voices

• list_voices — Search and browse voices on your account
• get_voice — Get full details for one voice by voice_id
• search_shared_voices — Search the public shared voice library (filters include accent)
• clone_voice — Create an instant voice clone from local audio samples (destructiveHint)
• delete_voice — Permanently delete a voice (destructiveHint)
• design_voice — Generate voice-design previews from a text description (slow; previews saved under the workspace)
• create_voice_from_preview — Save a design preview as a permanent voice (destructiveHint)

Speech & conversion

• generate_speech — Generate spoken audio from text using text-to-speech (supports seed and pronunciation_dictionary_locators)
• generate_speech_with_timestamps — Generate speech with character-level timing; also writes an .srt subtitle file and alignment JSON
• generate_sound_effect — Generate sound effects from a text description
• speech_to_speech — Convert source audio to a different voice
• text_to_dialogue — Multi-voice dialogue from a script (one voice per line)

History (FREE)

• list_history — List previously generated audio items (find that voiceover from last week)
• get_history_item_audio — Re-download the audio of a past generation by history_item_id

Pronunciation dictionaries

• list_pronunciation_dictionaries — List pronunciation dictionaries (brand names, jargon) (FREE)
• get_pronunciation_dictionary — Get one dictionary's metadata and current rules (FREE)
• add_pronunciation_dictionary — Create a dictionary from alias/IPA rules (destructiveHint)
• archive_pronunciation_dictionary — Archive a dictionary so it is no longer applied (destructiveHint; reversible in the dashboard)

Audio processing

• isolate_audio — Remove background noise from an audio file (source must be ≥ ~4.6s; shorter clips fail upstream)
• forced_alignment — Align transcript text to audio with per-word timestamps

Dubbing (v1 API — async submit → poll → download)

• create_dubbing — Submit a dubbing job (local file via sandbox or source_url for ElevenLabs-side fetch)
• get_dubbing — Poll job status until dubbed, failed, or cancelled
• download_dubbed_audio — Download dubbed audio (Content-Type sniffed)
• delete_dubbing — Permanently delete a dubbing job (destructiveHint)

Music

• generate_music — Generate music from a text prompt
• create_music_plan — Create a composition plan for music generation (free)
• generate_music_from_plan — Generate music from a composition plan

Transcription

• transcribe_audio — Transcribe speech from an audio file to text, with optional speaker diarization (diarize, num_speakers, diarization_threshold) and word-level timestamps (include_word_timestamps); scribe_v1 and scribe_v2 models

Local file paths for upload tools must be inside MCP_WORKSPACE_PATH (or os.tmpdir() when unset). See src/tools/file-input.ts. Generated and downloaded files (speech audio, subtitles, history/dubbing downloads, voice-design previews) are written into the same canonical workspace root with exclusive creation — existing files are never overwritten. See src/tools/path-safety.ts.

Licence

FSL-1.1-MIT — Functional Source License, Version 1.1, with MIT future licence. The software converts to MIT licence on 2030-04-08.

Host-authorized local inputs

files/readModes version 1 is an experimental extension used by these connectors, not part of the MCP standard. A compatible host (the app running the connector) decides which input files a tool call may read. The connector opens only the host-approved physical path, after resolving symlinks. The host supplies this permission information with each call; it is not a tool argument you need to set. Missing or invalid permission information, or a file absent from the approved list, stops the read.

Clients that do not negotiate this extension keep the connector's existing standalone file restrictions. This extension changes input-read permissions; existing output destinations, upload formats, size limits and file checks apply.