ElevenLabs MCP server for AI agents

Let Claude, ChatGPT or your own agent read ElevenLabs: 3 typed functions through one MCP server. No ElevenLabs API key needed.

Functions
3
Sign-in
Not needed
Works with
MCP, HTTP, Node, Python

Connect

Just ElevenLabs

An MCP server for ElevenLabs alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.

https://api.bowmark.ai/mcp/site/elevenlabs
Every site

One MCP server for ElevenLabs and every other site Bowmark covers. Your agent looks up what it needs and calls it.

https://api.bowmark.ai/mcp
Set it up in your client

Both need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.

Functions

Open a function to see its arguments, what it returns and how to call it.

Read 3
  • cloneVoiceCreates a new ElevenLabs voice cloned from one or more caller-supplied audio sample URLs (Instant Voice Cloning).

    Arguments

    NameTypeRequired
    args{ name: string; sampleUrls: string[]; description?: string }Yes

    Returns elevenlabsVoice

    interface elevenlabsVoice {
      voiceId: string;
      name: string;
      requiresVerification: boolean;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/elevenlabs/cloneVoice

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.elevenlabs.cloneVoice({});
  • listVoicesLists the voices in the caller's ElevenLabs account, or finds an existing voice by name and returns its voice id.

    Arguments

    NameTypeRequired
    args{ name?: string }No

    Returns elevenlabsVoiceListing[]

    interface elevenlabsVoiceListing {
      voiceId: string;
      name: string;
      category: string | null;
      description: string | null;
      labels: Record<string, string>;
      previewUrl: string | null;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/elevenlabs/listVoices

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.elevenlabs.listVoices({});
  • synthesizeConverts text into spoken audio (MP3 by default) using an ElevenLabs voice.

    Arguments

    NameTypeRequired
    args{ text: string; voiceId?: string; modelId?: string }Yes

    Returns elevenlabsSynthesisResult

    interface elevenlabsSynthesisResult {
      audioBase64: string;
      contentType: string;
      voiceId: string;
    }

    HTTP endpoint

    POST https://api.bowmark.ai/v1/sites/elevenlabs/synthesize

    Call it

    import { bowmark } from "@bowmark/web";
    
    const result = await bowmark.providers.elevenlabs.synthesize({});

Use it from code