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

Q: Can Claude Desktop play the audio generated by Cartesia (Voice AI)?

Your AI client retrieves the audio data using tools like ttsbytes and saves it to your local filesystem. You can then open those files in your default media player. Claude Web users might see custom UI elements if the connector supports audio rendering.

Q: What formats does Cartesia (Voice AI) accept in Claude Desktop for voice cloning?

Pass a five-second audio clip to the clonevoice tool. The file needs to be accessible on your local drive for the desktop app to read it. Clean, single-speaker audio produces the most accurate clone.

Q: Does this MCP Server send my local files to its servers through Claude Desktop?

Audio clips and text scripts passed to tools like sttbatch or ttsbytes travel to Cartesia's API endpoints for processing. Vinkius runs this connection through a V8 Isolate Sandbox, destroying the environment immediately after the request finishes. Your local filesystem remains private beyond the specific files you explicitly ask Claude to process.

Generate lifelike speech, clone audio clips, and run batch transcriptions directly inside Claude Desktop.

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 Desktop

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Text-to-Speech and Voice Cloning

The `tts_bytes` and `tts_sse` tools let you generate audio files or stream speech directly from your chat window. You feed Claude a script, and it returns high-fidelity audio using Cartesia's models. Need a specific sound? The `clone_voice` tool takes a five-second audio clip and creates a custom voice profile. Modifying existing audio works just as smoothly. Running `voice_changer_bytes` alters a speaker's vocal identity while keeping their original intonation intact. If you have two audio segments that need a bridge, `infill_bytes` generates the missing speech to connect them without obvious cuts.

Claude Desktop MCP Server Dictionary Control

The `create_pronunciation_dict` tool gives you exact control over how specific words sound. This fixes the common issue where text-to-speech models mispronounce industry terms or names. You can check your active rules using `list_pronunciation_dicts` and push changes through `update_pronunciation_dict`. Taking content global requires different accents and dialects. Calling `localize_voice` adapts an existing voice profile to a new language without losing the original speaker's characteristics. If a voice stops being useful, `delete_voice` removes it from your account entirely.

Agent Management and Batch STT

The `list_agents` tool pulls up every voice agent configured in your Cartesia account. You can drill down into specific agent performance by running `get_agent` or review conversation histories using `list_agent_calls`. Claude reads the call transcripts to help you analyze user interactions. Processing large amounts of audio requires a different approach than real-time streams. The `stt_batch` tool transcribes complete audio files into text, returning the data for Claude to summarize or format. Keeping an eye on costs is simple when you trigger `get_usage_credits` to check your billing metrics.

Setup guide

Set up Cartesia (Voice AI) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Cartesia (Voice AI) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Cartesia (Voice AI) MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under cartesia-voice-ai-mcp.

json

{
  "mcpServers": {
    "cartesia-voice-ai-mcp": {
      "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 Desktop

Open Settings, go to Developer, and click Edit Config. Add the server command to your claude_desktop_config.json file. Save the file and restart the application to load the tools.

Your AI client retrieves the audio data using tools like `tts_bytes` and saves it to your local filesystem. You can then open those files in your default media player. Claude Web users might see custom UI elements if the connector supports audio rendering.

Pass a five-second audio clip to the `clone_voice` tool. The file needs to be accessible on your local drive for the desktop app to read it. Clean, single-speaker audio produces the most accurate clone.

Tell Claude to map specific text strings to phonetic spellings. It calls `create_pronunciation_dict` to save these rules. Every subsequent text-to-speech generation will respect that custom mapping.

Audio clips and text scripts passed to tools like `stt_batch` or `tts_bytes` travel to Cartesia's API endpoints for processing. Vinkius runs this connection through a V8 Isolate Sandbox, destroying the environment immediately after the request finishes. Your local filesystem remains private beyond the specific files you explicitly ask Claude to process.

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