How to Use the ElevenLabs MCP in CrewAI

Q: How do CrewAI agents select the right ElevenLabs voice?

Your CrewAI casting agent uses listvoices to inspect your voice library. It then passes the chosen voice ID to the agent running the texttospeech tool for final synthesis.

Q: Can a CrewAI team manage my ElevenLabs subscription limits?

Yes, a supervisor agent can call getsubscriptioninfo to check your character usage. If the limit is close, the CrewAI team can halt generation or switch to a cheaper model using listmodels.

Q: How do CrewAI agents download generated ElevenLabs audio files?

The agent uses getdownloadlink to retrieve the direct URL for any historical generation. This allows other agents in the crew to fetch, process, or distribute the audio file.

Q: Can my crew delete voices?

Yes, an administrative agent can use deletevoice to remove outdated custom clones. This keeps your voice library organized without manual intervention.

Give your CrewAI multi-agent teams the power to speak and manage ElevenLabs voice clones using this 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 CrewAI

Create your Vinkius account to connect ElevenLabs to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous voice production in CrewAI teams

The `text_to_speech` tool allows your CrewAI voice agent to convert written briefs into high-quality audio files without human intervention. Your writer agent drafts the script, your editor agent reviews it, and your voice agent calls this tool to produce the final MP3. This multi-agent collaboration turns static text generation into a complete audio production line. Because the MCP Server handles the API details, your agents can focus on refining the script before generating the audio.

Multi-agent voice selection using this MCP Server

The `list_voices` tool gives your CrewAI casting agent the ability to inspect all available speakers and choose the best match. The agent reads the voice metadata to select an appropriate accent and gender for the target audience. This programmatic selection means your team can cast different voices dynamically for different roles in a dialogue. The MCP Server acts as the central voice registry for your entire autonomous crew.

Automated history auditing

The `list_audio_history` tool lets your CrewAI auditor agent monitor all voice outputs generated by the team. The auditor agent can download past audio files using `get_download_link` to verify quality or archive the results. This allows you to build self-correcting teams where a supervisor agent reviews the output history and orders regenerations if the tone is incorrect. No manual file management is needed.

Setup guide

Set up ElevenLabs MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke ElevenLabs tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="ElevenLabs Analyst",
    goal="Access and analyze ElevenLabs data via MCP.",
    backstory="Expert analyst with direct ElevenLabs access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent ElevenLabs transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="ElevenLabs Analyst",
        goal="Access and analyze ElevenLabs data via MCP.",
        backstory="Expert analyst with direct ElevenLabs access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent ElevenLabs transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Your CrewAI casting agent uses `list_voices` to inspect your voice library. It then passes the chosen voice ID to the agent running the `text_to_speech` tool for final synthesis.

Yes, a supervisor agent can call `get_subscription_info` to check your character usage. If the limit is close, the CrewAI team can halt generation or switch to a cheaper model using `list_models`.

The agent uses `get_download_link` to retrieve the direct URL for any historical generation. This allows other agents in the crew to fetch, process, or distribute the audio file.

Yes, an administrative agent can use `delete_voice` to remove outdated custom clones. This keeps your voice library organized without manual intervention.

This MCP Server processes your generated audio history and voice clone metadata through secure, ephemeral sandbox environments. No voice profiles or generated audio logs are stored on Vinkius servers, ensuring complete privacy for your biometric assets.

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