How to Use the Cartesia (Voice AI) MCP in AutoGen

Q: How do I add Cartesia (Voice AI) tools to my AutoGen agents?

Install autogen-extmcp. Initialize mcpservertools with your Vinkius HTTP endpoint, and pass the resulting tool list directly into your AssistantAgent constructor.

Q: How does AutoGen handle the binary audio output from Cartesia?

The McpToolAdapter handles the schema conversion. Your agent receives the base64-encoded audio bytes from ttsbytes and writes them to a local file or passes them to another service in the chat.

Q: Can my agents debate which voice profile to use?

That is the core strength of the framework. Agents call listvoices, review the available metadata, and negotiate which profile best fits the current script before generating anything.

Give your AutoGen multi-agent systems the ability to generate, clone, and critique audio with Cartesia.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cartesia (Voice AI) MCP to AutoGen

Create your Vinkius account to connect Cartesia (Voice AI) to AutoGen 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 Cartesia (Voice AI) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent audio production

You can build a system where a Director agent writes a script and passes it to a Voice Actor agent equipped with `tts_bytes`. AutoGen thrives on collaboration between specialized roles. The Voice Actor generates the audio and returns it to the group. A separate Quality Assurance agent then reviews the output. If the pacing feels wrong, the QA agent instructs the Voice Actor to tweak the parameters or use `voice_changer_bytes` to adjust the delivery. They debate and iterate until the audio meets the required standard.

Manage your Cartesia MCP Server assets

A dedicated Admin agent monitors your account by calling `get_usage_credits` and alerting the group if you approach your limit. Delegating infrastructure tasks to conversational agents saves massive amounts of time. You don't need to check dashboards manually. This Admin agent cleans up resources autonomously. It fetches unused profiles via `list_voices`, proposes a cleanup plan, waits for human approval in the chat, and executes `delete_voice` to keep your Cartesia workspace tidy.

Complex voice cloning workflows

An Audio Engineer agent extracts a clean 5-second segment and feeds it into `clone_voice` to register a new speaker. Voice cloning requires precision inside an MCP workflow. The agent evaluates the raw user upload for quality before doing anything. The workflow keeps going after the clone registers. The Engineer immediately tests the clone, generates a sample, and uses `infill_bytes` to drop that sample into a larger pre-recorded track. Multiple agents coordinate the entire post-production process without human intervention.

Setup guide

Set up Cartesia (Voice AI) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Cartesia (Voice AI) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Cartesia (Voice AI)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Cartesia (Voice AI) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Cartesia (Voice AI)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Cartesia (Voice AI) data")
    print(result.messages[-1].content)

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 Cartesia. 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 Cartesia (Voice AI) 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 Cartesia (Voice AI) MCP in AutoGen

Install `autogen-ext[mcp]`. Initialize `mcp_server_tools` with your Vinkius HTTP endpoint, and pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes. You equip different agents with the exact same toolset, or distribute specific tools. One agent might handle `stt_batch` for input, while another only has access to `tts_sse` for output.

The `McpToolAdapter` handles the schema conversion. Your agent receives the base64-encoded audio bytes from `tts_bytes` and writes them to a local file or passes them to another service in the chat.

That is the core strength of the framework. Agents call `list_voices`, review the available metadata, and negotiate which profile best fits the current script before generating anything.

Security is baked into the infrastructure. The MCP server processes your voice clones and transcription payloads inside an ephemeral sandbox. Vinkius destroys the environment immediately after the tool call finishes, leaving no trace of your raw audio.

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