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

Q: Can Windsurf use Cartesia (Voice AI) to clone a voice automatically?

Yes, Cascade can execute clonevoice autonomously when you provide a path to a five-second audio file. It handles the upload, triggers the cloning process, and saves the new voice ID to your workspace.

Q: How does Windsurf handle pronunciation dictionaries with Cartesia (Voice AI)?

Cascade uses createpronunciationdict and updatepronunciationdict to manage custom spelling rules. When it detects pronunciation issues in your generated audio, it updates the dictionary and regenerates the clip.

Generate and clone lifelike voices with Cartesia (Voice AI) using Cascade's autonomous agent chains in Windsurf.

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 Windsurf

Create your Vinkius account to connect Cartesia (Voice AI) to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run complex voice cloning pipelines in Windsurf

This MCP Server exposes voice manipulation tools like `clone_voice` and `localize_voice` to let Cascade build entire voice libraries from audio files. You provide a short audio clip, and the agent clones the voice and adapts it to different dialects in one autonomous run. Cascade plans the sequence, executes the cloning, and updates the metadata with `update_voice` without asking for permission at every step. You get a cloned voice ready for production without writing a single line of integration code.

Build text-to-speech audio pipelines

The server generates raw audio bytes and server-sent events using `tts_bytes` and `tts_sse`. Cascade can parse your text documents, plan the chunking, and feed them into these tools to produce clean voiceovers. It handles errors and retries by itself. If a word sounds off, Cascade corrects the pronunciation instantly using `create_pronunciation_dict` before regenerating the audio.

Manage voice agents and billing metrics

This toolset lets Cascade fetch your active voice agents and monitor your balance using `list_agents` and `get_usage_credits`. Your agent can check how much credit you have left before initiating a massive transcription or voice generation job. It can also retrieve transcripts and call logs using `list_agent_calls`. You get a clear picture of your voice agent operations directly inside your IDE panel.

Setup guide

Set up Cartesia (Voice AI) MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Cartesia (Voice AI) payment history." If connected, Cascade will call the Cartesia (Voice AI) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Open your Windsurf settings and add the server configuration under the mcpServers key in ~/.codeium/windsurf/mcp_config.json. You can also use the Cascade MCP Servers UI to paste the Vinkius connection URL. Cascade will auto-discover all twenty voice tools immediately.

Yes, Cascade can execute `clone_voice` autonomously when you provide a path to a five-second audio file. It handles the upload, triggers the cloning process, and saves the new voice ID to your workspace.

Cascade uses `create_pronunciation_dict` and `update_pronunciation_dict` to manage custom spelling rules. When it detects pronunciation issues in your generated audio, it updates the dictionary and regenerates the clip.

You cannot play live audio streams directly inside the editor, but Cascade can use `tts_sse` to stream the audio data to local files. You can then play these generated WAV or MP3 files from your workspace.

All voice prints, raw audio data, and text transcripts are processed inside a zero-trust V8 Isolate Sandbox on Vinkius. This MCP setup ensures your sensitive audio files are never stored permanently on the server. Every session is ephemeral and runs in isolation.

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