Cartesia MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Cartesia MCP or direct API to generate speech, transcribe audio, manage voices, and build voice agents through natural language.

Cartesia logoCartesia
Api Key

Cartesia is a real-time voice AI platform for text-to-speech, speech-to-text, and managed voice agents. It helps developers build fast, natural voice experiences with powerful audio APIs.

10 Tools

Try Cartesia now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Cartesia
Try asking
TOOLS

Supported Tools

Every Cartesia action and event your agent gets out of the box.

Create Pronunciation Dictionary

Create a reusable pronunciation dictionary for text-to-speech generation.

Delete Pronunciation Dictionary

Permanently delete one pronunciation dictionary by ID.

Get Pronunciation Dictionary

Return one pronunciation dictionary and its complete text-to-pronunciation mappings.

Get Voice

Return synthesis-relevant details for one Cartesia voice by ID.

List Accents

List supported accents, optionally filtered by language, locale, or voice-localization support.

List Agent Models

List language models available to Cartesia Managed Agents, including provider, latency, and pricing metadata.

List Pronunciation Dictionaries

Return one page of pronunciation dictionaries available to the connected account.

List Voices

Search and filter Cartesia voices, returning one page of voice IDs and synthesis-relevant metadata.

Synthesize Speech

Generate a downloadable audio file from one complete transcript using a selected Cartesia voice; usage is billed by transcript length.

Update Pronunciation Dictionary

Update a pronunciation dictionary and replace its mappings with the complete supplied item set.

SETUP GUIDE

Connect Cartesia MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["cartesia"],
  mcp: true,
});
Create a session scoped to Cartesia and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Convert the text 'Your order has shipped and will arrive tomorrow.' to speech using Cartesia and return the generated audio.",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a Cartesia request
SETUP GUIDE

Connect Cartesia API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["cartesia"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Cartesia
3

Run Cartesia tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Convert the text 'Your order has shipped and will arrive tomorrow.' to speech using Cartesia and return the generated audio." }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the Cartesia tool calls through the session, and print the final answer

Why Use Composio?

AI Native Cartesia Integration

  • Supports both Cartesia MCP and direct API integrations
  • Structured, LLM-friendly schemas for reliable speech and transcription tool execution
  • Rich coverage for generating audio, transcribing speech, and managing voice workflows

Managed Auth

  • Securely stores and applies your Cartesia API keys to requests
  • Central place to manage, scope, and revoke Cartesia access
  • Per user and per environment credentials instead of hard-coded keys

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Clear schemas help agents choose the right Cartesia voice, model, and audio settings
  • Comprehensive execution logs show what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Cartesia
  • Scoped, least privilege access to Cartesia voice and audio resources
  • Full audit trail of agent actions to support review and compliance

Rolling this out across your team?

Give your team centralized access control across every framework with Composio’s MCP Gateway.

EXPLORE MCP GATEWAY
FAQ

Frequently asked questions

Start with Cartesia.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Cartesia tool your agent needs.Free to start.

Start building