How to Use the Cartesia (Voice AI) MCP in Vercel AI SDK

Q: How do I connect Cartesia (Voice AI) to Vercel AI SDK?

Use createMCPClient with your Vinkius URL. Call mcpClient.tools() to grab the functions, then pass them straight into streamText to start generating audio.

Q: Can I stream audio directly to the browser?

Yes. The ttssse tool is specifically built for Server-Sent Events, which pairs perfectly with this client's streaming architecture.

Stream Cartesia voice generation and transcription directly into your Next.js frontend using Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Cartesia (Voice AI) to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time speech streaming

You want audio playing while the text generates. Vercel AI SDK handles the frontend streaming, and the `tts_sse` tool pushes the audio chunks as they render. Your users never stare at a loading spinner. If you need raw files instead of streams, `tts_bytes` grabs the complete audio payload for immediate playback.

Voice cloning via MCP Server

Building a voice cloning app requires fast feedback. Pass a five-second clip to `clone_voice` and your agent registers the new profile immediately. Adapting that exact voice to different languages works through `localize_voice`. The entire process happens server-side while your UI stays responsive.

Custom pronunciation rules

Text-to-speech engines mispronounce industry terms constantly. Fix this by calling `create_pronunciation_dict` to force the exact phonetic output you need. Update those rules on the fly with `update_pronunciation_dict`. Your Next.js app applies the dictionary to all subsequent generation requests automatically.

Setup guide

Set up Cartesia (Voice AI) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Cartesia (Voice AI) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Cartesia (Voice AI) transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Use `createMCPClient` with your Vinkius URL. Call `mcpClient.tools()` to grab the functions, then pass them straight into `streamText` to start generating audio.

Yes. The `tts_sse` tool is specifically built for Server-Sent Events, which pairs perfectly with this client's streaming architecture.

Yes, and it happens fast. Send a short audio clip through the specific tool, and the new voice becomes available for immediate generation.

Vinkius handles the underlying credentials. You just pass your single endpoint token in the setup, and the `generate_access_token` tool manages client-side requests.

We run this MCP integration in an isolated V8 sandbox. Your text prompts and five-second voice samples pass directly to the API and disappear from our memory immediately.

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