How to Use the ElevenLabs MCP in Mastra AI

Q: How does Mastra AI fetch my custom ElevenLabs voice profiles?

The framework uses the listvoices tool to retrieve your voice catalog during agent initialization. Mastra AI can then route tasks to specific voices based on the workflow state.

Q: Can my Mastra AI agent delete historical ElevenLabs audio records?

Yes, your agent can call deletehistoryitem to purge specific generation logs. This is ideal for automated compliance workflows that require immediate data deletion after processing.

Q: How do I check my plan limits?

Use the getsubscriptioninfo tool to monitor your character balance. Mastra AI can branch its workflow based on this data, halting execution or sending an alert if your balance runs low.

Run ElevenLabs speech generation inside your Mastra AI workflow using this dedicated MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ElevenLabs MCP to Mastra AI

Create your Vinkius account to connect ElevenLabs to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup ElevenLabs with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated voice generation in Mastra AI workflows

The `text_to_speech` tool fits directly into your Mastra AI state machine to generate voiceovers during background processing. If the API hits a rate limit, the Mastra AI workflow engine automatically retries with exponential backoff. This setup ensures your automated video or podcast generation pipelines never fail due to transient network issues. You write the workflow logic once, and this MCP Server handles the audio generation reliably.

Dynamic voice auditing with this MCP Server

The `list_audio_history` tool lets your Mastra AI workflows monitor and audit every generated ElevenLabs audio file automatically. Your agent can scan past generations to track character consumption or verify that output files were generated successfully. By feeding this history data back into your workflow, you can trigger automated cleanups or generate usage reports. The MCP Server acts as a direct bridge between your ElevenLabs history and your Mastra database.

Automated voice lifecycle management

The `delete_voice` tool allows your Mastra AI agent to programmatically remove temporary voice clones once a job finishes. This prevents your ElevenLabs account from cluttering up with single-use cloned voices. You can build workflows that clone a voice, generate the required speech files, and then purge the source clone automatically. This keeps your storage usage lean and your operational costs predictable.

Setup guide

Set up ElevenLabs MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All ElevenLabs tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "elevenlabs-alternative-mcp-client",
  servers: {
    "elevenlabs-alternative-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "ElevenLabs Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to ElevenLabs tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent ElevenLabs transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ElevenLabs. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect ElevenLabs now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about ElevenLabs MCP in Mastra AI

Yes, you can configure your Mastra AI workflow to catch errors from `text_to_speech` and automatically retry. This prevents temporary ElevenLabs API bottlenecks from breaking your background processing pipelines.

The framework uses the `list_voices` tool to retrieve your voice catalog during agent initialization. Mastra AI can then route tasks to specific voices based on the workflow state.

Yes, your agent can call `delete_history_item` to purge specific generation logs. This is ideal for automated compliance workflows that require immediate data deletion after processing.

Use the `get_subscription_info` tool to monitor your character balance. Mastra AI can branch its workflow based on this data, halting execution or sending an alert if your balance runs low.

This MCP Server handles your custom voice clones and generation history using zero-trust credentials. Your ElevenLabs voice data is processed within a secure, ephemeral V8 isolate sandbox that vanishes immediately after execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript