ElevenLabs runs on your own machine — the client starts it, so there is no endpoint to ping. 119 installs a week from npm. Last commit 2 Nov 2026.
ElevenLabs MCP server: TTS, music, sound effects, voices, and audio transcription
Nothing serious here today
Today is the operative word: we check ElevenLabs every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server-elevenlabs -e 'ELEVENLABS_API_KEY=<ELEVENLABS_API_KEY>' -- npx -y @mindstone/mcp-server-elevenlabs{
"mcpServers": {
"mcp-server-elevenlabs": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-elevenlabs"
],
"env": {
"ELEVENLABS_API_KEY": "<ELEVENLABS_API_KEY>"
}
}
}
}[mcp_servers.mcp-server-elevenlabs]
command = "npx"
args = ["-y", "@mindstone/mcp-server-elevenlabs"]
env = { ELEVENLABS_API_KEY = "<ELEVENLABS_API_KEY>" }{
"mcpServers": {
"mcp-server-elevenlabs": {
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-elevenlabs"
],
"env": {
"ELEVENLABS_API_KEY": "<ELEVENLABS_API_KEY>"
}
}
}
}{
"servers": {
"mcp-server-elevenlabs": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mindstone/mcp-server-elevenlabs"
],
"env": {
"ELEVENLABS_API_KEY": "<ELEVENLABS_API_KEY>"
}
}
}
}Put your own value in place of
<ELEVENLABS_API_KEY> (ElevenLabs API key (starts with sk_)).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
MCP_WORKSPACE_PATH (Workspace directory for transcription audio file inputs. Defaults to os.tmpdir() when unset).
Alternatives to ElevenLabs
same job, measured the same wayManage ElevenLabs voice agents and generate speech, music, sound effects, images, and video.
Generate speech, voices, and transcripts through the ElevenLabs API.
AI music and sound effects for games and videos: Suno, Lyria, Stable Audio, MiniMax, ElevenLabs.
Voice Audio MCP server. Tools: text to speech, list voices, transcribe. Built by MEOK AI Labs.
Audio for your agent: transcribe, speak, translate, summarise, plus sound effects and music.
MCP server for ElevenLabs Conversational AI (not TwelveLabs video) — agents, KB, voices
High-performance audio, music, and voice generation MCP server for Gemini 2.5 and Lyria 3.
Local MCP server, eight music tools: OMR, transcription, theory and notation checks, convert.
ElevenLabs — questions
Answers built from our own checks of this server.