How to Use the Cartesia (Voice AI) MCP in Claude Code

Q: How do I add the Cartesia (Voice AI) MCP Server to Claude Code?

Run the command claude mcp add --transport http cartesia -- in your terminal, replacing the placeholder with your Vinkius endpoint URL. You can verify the installation by running claude mcp list.

Q: Can I check my API credit usage from the terminal?

Yes, Claude Code can run getusagecredits to show your active balance and usage metrics. This helps you monitor costs directly from your command line.

Pipe terminal outputs to lifelike speech using Claude Code and the Cartesia (Voice AI) MCP Server.

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 Claude Code

Create your Vinkius account to connect Cartesia (Voice AI) to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate voice generation in Claude Code

This MCP Server lets you generate audio files from CLI commands using `tts_bytes` and `infill_bytes`. Claude Code can pipe terminal outputs, build logs, or system alerts straight into the text-to-speech engine to generate status voiceovers. You can integrate these tools into your bash scripts and cron jobs. The agent runs headless, generating voice notifications whenever a production deployment completes or fails.

Headless voice cloning and translation

The server allows you to clone and localize voices via `clone_voice` and `localize_voice` using simple terminal prompts. Claude Code can pull audio files from remote servers, run the cloning process, and output localized voice assets. It can also manage your voice library using `delete_voice` and `update_voice`. You control your entire voice infrastructure using standard terminal inputs.

Batch transcribe audio from the terminal

This toolset transcribes audio files and manages voice agents using `stt_batch` and `get_agent`. Claude Code can scan directories for audio recordings, run batch transcriptions, and pipe the text output to other terminal utilities. You can automate your audio analysis pipelines without a GUI. The agent handles the file processing and outputs clean, structured transcripts.

Setup guide

Set up Cartesia (Voice AI) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see cartesia-voice-ai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Cartesia (Voice AI) transactions." It will automatically discover and invoke the available Cartesia (Voice AI) tools.

Terminal

claude mcp add --transport http cartesia-voice-ai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Cartesia (Voice AI) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "cartesia-voice-ai-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

Run the command `claude mcp add --transport http cartesia -- ` in your terminal, replacing the placeholder with your Vinkius endpoint URL. You can verify the installation by running `claude mcp list`.

Yes, you can run Claude Code headlessly to trigger tools like `tts_bytes` during your build steps. This lets you generate automated voice alerts or audio documentation on every commit.

You can pass a local audio path to Claude Code, and it will call `clone_voice` to create a new voice model. The agent will output the new voice ID directly to your terminal.

Yes, Claude Code can run `get_usage_credits` to show your active balance and usage metrics. This helps you monitor costs directly from your command line.

All audio files, voice prints, and text transcripts are processed in a secure, zero-trust V8 sandbox on Vinkius. This secure MCP environment handles data ephemerally and wipes it immediately after execution, ensuring your voice biometric data never leaks.

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