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

Q: Can I generate client-side tokens for Cartesia (Voice AI) using VS Code Copilot?

Ask Copilot to execute the generateaccesstoken tool. It returns a short-lived credential perfect for testing frontend components without exposing your primary API keys.

Q: How do we track API usage for Cartesia (Voice AI) in VS Code Copilot?

Any developer can call the getusagecredits tool through the chat panel. This provides immediate visibility into how many credits the team has consumed during the current billing cycle.

Q: What is the best way to test pronunciation changes with Cartesia (Voice AI) and VS Code Copilot?

Use createpronunciationdict to define the rule, then immediately run ttsbytes with a test phrase. Copilot handles the tool chaining so you hear the result in seconds.

Q: Are my voice models secure when using the Cartesia (Voice AI) MCP Server in VS Code Copilot?

Transcripts pulled via listagentcalls and voice metadata route through the Vinkius infrastructure. We rely on stateless, ephemeral execution environments that spin down instantly. Neither Vinkius nor the AI client retains your proprietary conversation logs after the session ends.

Give your entire engineering team access to Cartesia (Voice AI) directly inside VS Code Copilot.

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 VS Code Copilot

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Custom Voice Deployment

The `clone_voice` tool takes a five-second sample and returns a usable voice ID for your application. When you commit the MCP Server configuration to your repository, every developer gets instant access to generate these profiles. Team members can also pull existing configurations using `list_voices` and `get_voice`. Managing these assets across an organization requires strict control. Running `update_voice` lets developers adjust metadata, while `delete_voice` cleans up deprecated test clones. If a project expands to new regions, `localize_voice` adapts your standard brand voices to different languages without needing new voice actors.

VS Code Copilot MCP Server Audio

The `tts_bytes` tool generates raw audio data from text inputs. Copilot can write the API request logic, execute the tool, and verify the binary response structure matches your expectations. For low-latency applications, `tts_sse` streams the audio back in chunks. Complex audio workflows often require post-processing. Calling `voice_changer_bytes` swaps the vocal identity of a source file, which helps teams test different character voices quickly. If your application stitches audio together, `infill_bytes` creates smooth bridges between disconnected clips.

Pronunciation Rules and Analytics

The `create_pronunciation_dict` tool ensures your entire team uses consistent phonetic spellings for brand names or technical terms. Developers can update these mappings using `update_pronunciation_dict` as the product evolves. Anyone on the team can check the current rules by running `list_pronunciation_dicts`. Debugging voice agents requires actual conversation data. The `list_agent_calls` tool fetches transcripts and call metadata directly into your editor. Copilot analyzes these logs to identify where users drop off, while `stt_batch` handles offline transcription tasks for bulk audio analysis.

Setup guide

Set up Cartesia (Voice AI) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Cartesia (Voice AI) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Cartesia (Voice AI) tools listed. Try asking: "List my recent Cartesia (Voice AI) transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Add a .vscode/mcp.json file to your project repository. Include the MCP configuration in the mcpServers object. When your team pulls the latest commit, VS Code automatically registers the tools.

Ask Copilot to execute the `generate_access_token` tool. It returns a short-lived credential perfect for testing frontend components without exposing your primary API keys.

Any developer can call the `get_usage_credits` tool through the chat panel. This provides immediate visibility into how many credits the team has consumed during the current billing cycle.

Use `create_pronunciation_dict` to define the rule, then immediately run `tts_bytes` with a test phrase. Copilot handles the tool chaining so you hear the result in seconds.

Transcripts pulled via `list_agent_calls` and voice metadata route through the Vinkius infrastructure. We rely on stateless, ephemeral execution environments that spin down instantly. Neither Vinkius nor the AI client retains your proprietary conversation logs after the session ends.

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