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

Q: How do I connect the Cartesia (Voice AI) MCP server to Pydantic AI?

Run pip install pydantic-ai-slimmcp. Initialize MCPToolset with your Vinkius HTTP URL. Pass that toolset directly to your Agent constructor via the toolsets array.

Q: Does Pydantic AI support streaming from Cartesia (Voice AI)?

It does. The server exposes the ttssse tool for Server-Sent Events. Pydantic AI handles the Streamable HTTP transport natively, giving you audio chunks in real time.

Q: Can I transcribe audio files using Cartesia (Voice AI) in Pydantic AI?

Yes. You trigger the sttbatch tool. The agent sends the audio file, and the framework strictly validates the returned text transcript against your predefined schemas.

Q: How do I manage voice agents programmatically?

The server provides listagents to show your active deployments. You retrieve specific configuration details using the getagent tool. Every response fails loudly if the JSON structure changes unexpectedly.

Bring type-safe audio generation to Pydantic AI. Connect Cartesia's sonic models and validate every voice clone or transcript at runtime.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pydantic AI Cartesia MCP Server tools

You care about strict data contracts. This MCP Server exposes `tts_bytes` to your agent, and Pydantic AI validates the raw byte output before your application ever sees it. If the API returns garbage, the framework throws a validation error immediately. Voice management gets the same treatment. Your agent calls `list_voices` to see what is available. It grabs a specific profile with `get_voice`, and you know the resulting metadata matches your exact schema definitions.

Type-safe voice cloning

Audio manipulation requires exact parameters. The `clone_voice` tool takes a short audio clip and returns a new voice ID. You adapt that voice to new languages using `localize_voice`, knowing the inputs align perfectly with your models. Splicing audio is just as precise. You pass two audio segments to `infill_bytes`, and the server generates the connecting speech. If you need to swap a speaker's identity, `voice_changer_bytes` does the job while preserving the original intonation.

Strict pronunciation controls

Custom dictionaries prevent embarrassing audio mistakes. You build them using `create_pronunciation_dict` to force the engine to say specific words correctly. If a rule becomes obsolete, `delete_pronunciation_dict` removes it from the system entirely. You need to track what your voice agents actually say. The `list_agent_calls` tool returns full transcripts for any specific agent. You also track your exact billing metrics by calling `get_usage_credits` so you never exceed your budget.

Setup guide

Set up Cartesia (Voice AI) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "cartesia-voice-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Cartesia (Voice AI) tools.",
)

result = await agent.run("List recent Cartesia (Voice AI) transactions")
print(result.output)

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 Pydantic AI

Run pip install pydantic-ai-slim[mcp]. Initialize MCPToolset with your Vinkius HTTP URL. Pass that toolset directly to your Agent constructor via the toolsets array.

It does. The server exposes the tts_sse tool for Server-Sent Events. Pydantic AI handles the Streamable HTTP transport natively, giving you audio chunks in real time.

Yes. You trigger the stt_batch tool. The agent sends the audio file, and the framework strictly validates the returned text transcript against your predefined schemas.

The server provides list_agents to show your active deployments. You retrieve specific configuration details using the get_agent tool. Every response fails loudly if the JSON structure changes unexpectedly.

Your batch audio files and resulting transcripts run through an ephemeral V8 sandbox. Vinkius requires only a single endpoint token for authentication. Once the Pydantic AI session closes, the memory drops, leaving zero residual data behind.

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