ElevenLabs MCP Server
✓ verifiedText-to-speech, voice cloning, and audio transcription.
Don't have ToolPiper? We'll take you to the download.
Publisher
License
MIT
Transport
Local subprocess
Tools
4
What this server does
ElevenLabs' MCP server brings high-quality text-to-speech, transcription, and voice cloning into chat. Generate narration in any of your voices, clone a new voice from short samples, transcribe recordings, and list the voices on your account. Useful for drafting voiceover, prototyping audio UX, or transcribing meetings. Output audio is generated against your ElevenLabs account, which bills per character synthesized.
Tools included
text_to_speech
Synthesize speech from text in a chosen voice.
speech_to_text
Transcribe an audio file to text.
voice_clone
Create a cloned voice from audio samples.
list_voices
List available voices.
The authoritative list comes from the server's tools/list at runtime. This catalog entry may lag the upstream until the next ToolPiper release.
Install in ToolPiper
ToolPiper handles the JSON configuration. Click Install, fill in any required tokens, and the server is ready in your chat.
Don't have ToolPiper? We'll take you to the download.
Install in another client
Install in another MCP client (Claude Desktop, Cursor, Continue, Cline)
Add this to ~/Library/Application Support/Claude/claude_desktop_config.json.
{
"mcpServers": {
"elevenlabs": {
"command": "uvx",
"args": [
"elevenlabs-mcp"
]
}
}
}Example prompts
"Read this paragraph aloud in a calm narrator voice and save the audio."
"Transcribe this interview recording and give me a clean transcript."
"List my available voices and tell me which are cloned."
Security notes
The API key bills against your ElevenLabs account on every synthesis and clone, with no spend cap inside the server, so an agent in a loop can run up charges. Treat the key as a credential and rotate it if it leaks. Voice cloning of a real person's voice carries consent and impersonation risks; only clone voices you are authorized to use.