How to integrate Cartesia MCP with Atomic Agent

Connect Atomic Agent to Cartesia MCP. Convert text to speech with cartesia, transcribe a cartesia audio recording, and more using natural language, with authentication handled for you.

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

Introduction

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,500+ apps through Composio, including Cartesia.

This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a Cartesia account. See the Atomic Agent documentation for installation instructions.

Also integrate Cartesia with

How Atomic Agent connects to Cartesia

Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.

Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

Connect Cartesia to Atomic Agent

  1. Sign up or sign in to the Composio dashboard. Copy your API key.
  2. In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
  3. Ask Atomic Agent to do something in Cartesia. It searches Composio for the right tool.
  4. On first use, open the sign-in link returned in the chat. Connect your Cartesia account, then return to Atomic Agent to continue.

Headless setup

Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

bash
COMPOSIO_API_KEY=YOUR_COMPOSIO_API_KEY

What is the Cartesia MCP server, and what's possible with it?

The Cartesia MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Cartesia account. It provides structured and secure access to voice, speech synthesis, pronunciation dictionary, accent, and managed agent model capabilities, so your agent can generate audio from text, find suitable voices, check supported accents, manage pronunciation dictionaries, and review available agent models on your behalf.

  • Text-to-speech generation: Have your agent turn a complete transcript into a downloadable audio file using a selected Cartesia voice.
  • Voice discovery: Let the agent search Cartesia voices and retrieve synthesis details to help choose the right voice for an audio project.
  • Accent exploration: Direct your agent to list supported accents and filter them by language, locale, or voice localization support.
  • Pronunciation dictionary management: Instruct your agent to create, review, update, list, or delete reusable pronunciation dictionaries for more consistent speech generation.
  • Managed agent model selection: Have your agent review available Cartesia managed agent models, including provider, latency, and pricing details.

Use Cartesia from Atomic Agent

With your account connected, ask Atomic Agent to work with Cartesia in natural language. You can connect more apps through the same Composio integration as you need them.

Visit the Atomic Agent website or inspect the Atomic Agent source code.

Troubleshooting

Why is my API key rejected?

Copy the key directly from the Composio dashboard. Atomic Agent requires ASCII characters because it sends the key in an HTTP header. Remove any extra characters introduced when copying.

Why are Composio tools unavailable after saving a key?

Check that you use Atomic Agent v0.5.6 or later and that Composio is enabled in your configuration. A "composio": { "enabled": false } setting disables the integration while keeping the saved key on disk.

Does Composio have a free plan?

The Hobby plan includes 100,000 tool calls per month. Composio-managed OAuth apps have a lower included allowance. See Composio pricing for the current limits that apply to your connection.

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.

FAQ

Frequently asked questions

With a standalone Cartesia MCP server, the agents and LLMs can only access a fixed set of Cartesia tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Cartesia and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Atomic Agent fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Cartesia tools.

Yes, absolutely. You can configure which Cartesia scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Cartesia data and credentials are handled as safely as possible.

Start with Cartesia.It takes 30 seconds.

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

Start building