An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Cartesia Voice AI to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Give your AI agent a human voice.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 20 capabilities

We ship only the actions that matter.

Capability set01 / 05

01-04

4 capabilities in this set.

Part of 20 available through Cartesia.

  1. 01

    Delete pronunciation dict

    Remove an existing pronunciation dictionary.

  2. 02

    Generate access token

    Create a short-lived token for client-side requests.

  3. 03

    Get agent

    Pull detailed information about a specific voice agent.

  4. 04

    Get usage credits

    Check your current credit balance and usage stats.

Capability set02 / 05

05-08

4 capabilities in this set.

Part of 20 available through Cartesia.

  1. 05

    Infill bytes

    Generate audio to bridge the gap between two existing audio segments.

  2. 06

    List agent calls

    View call logs and transcripts for a specific agent.

  3. 07

    List voices

    Retrieve a list of all available voices.

  4. 08

    List agents

    Get a list of all your configured voice agents.

Capability set03 / 05

09-12

4 capabilities in this set.

Part of 20 available through Cartesia.

  1. 09

    List pronunciation dicts

    See all the pronunciation dictionaries you have created.

  2. 10

    Tts sse

    Stream text-to-speech audio using Server-Sent Events.

  3. 11

    Update pronunciation dict

    Edit the contents of a pronunciation dictionary.

  4. 12

    Stt batch

    Transcribe an entire audio file into text.

Capability set04 / 05

13-16

4 capabilities in this set.

Part of 20 available through Cartesia.

  1. 13

    Tts bytes

    Generate audio bytes from text.

  2. 14

    Clone voice

    Create a new voice clone using a 5-second audio sample.

  3. 15

    Create pronunciation dict

    Set up a new pronunciation dictionary for specific words.

  4. 16

    Delete voice

    Delete a specific voice from your library.

Capability set05 / 05

17-20

4 capabilities in this set.

Part of 20 available through Cartesia.

  1. 17

    Get voice

    Get specific details for a single voice.

  2. 18

    Localize voice

    Adapt an existing voice to a different language or dialect.

  3. 19

    Update voice

    Modify the metadata for a specific voice.

  4. 20

    Voice changer bytes

    Swap the voice in an audio clip while keeping the original intonation.

Real work

What teams actually run

01

Conversational AI

Give your agent a human-sounding voice for real-time phone or web interactions.

02

Automated Voiceovers

Turn text into high-quality audio files for videos or podcasts.

03

Audio Localization

Adapt a specific voice to speak in a new language or dialect.

04

Transcription Services

Convert large batches of audio files into text automatically.

Automate a task

Put Cartesia to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Cartesia works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Cartesia to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1045ms average. Fast in production.

Cartesia is checked daily against the live service.

Daily averagePeak 1469ms
Oct 3Today
Fastest day
837ms
Slowest day
1469ms
14-day trend
Stable+4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 20 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Cartesia, so you can see the experience inside your AI.

It does not authenticate your account with Cartesia. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Cartesia Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_fqUkC4o6TEWq9kAU8DlY8MAb7pfJxo3R952S85p7/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Cartesia capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "cartesia-voice-ai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_fqUkC4o6TEWq9kAU8DlY8MAb7pfJxo3R952S85p7/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Cartesia in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Cartesia owners hand off.

This MCP is built for anyone building interactive voice experiences that require speed and high fidelity.

  • 01

    Developers

    Building real-time voice features without managing audio infrastructure.

  • 02

    Content Creators

    Automating voiceovers and localizing audio using cloned voices.

  • 03

    Product Teams

    Creating conversational agents that respond with sub-second latency.

FAQ

Questions Cartesia owners ask.

  • 01

    How much audio do I need to clone a voice?

    You only need a 5-second audio clip to create a custom voice model.

  • 02

    Can I use this with Claude or Cursor?

    Yes, once you connect the MCP, you can use these capabilities within Claude, Cursor, Windsurf, or any other MCP-compatible client.

  • 03

    How do I handle technical terms that the AI mispronounces?

    You can create and manage custom pronunciation dictionaries to ensure the agent uses the correct sounds for specific words.

  • 04

    Is the audio generation fast enough for live calls?

    Yes, the Sonic models are designed for high performance and low latency, making them suitable for real-time applications.

  • 05

    How do I check how many credits I have left?

    You can use the get_usage_credits capability to see your current credit balance and usage statistics.

  • 06

    Can I generate audio in different formats like MP3 or WAV?

    Yes. Using the tts_bytes capability, you can specify the output_format_container as 'mp3', 'wav', or 'raw', and configure the sample rate and encoding to match your needs.

  • 07

    How do I transcribe an existing audio file to text?

    Use the stt_batch capability. Provide the base64 encoded audio file, specify the model (e.g., 'ink-whisper'), and the language code to receive a full transcription.

  • 08

    Is it possible to clone a voice using this integration?

    Absolutely. The clone_voice capability allows you to create a new voice model by uploading a short (approx. 5s) base64 encoded audio clip.

Explore

More in AI Frontier

Suggestions

Connect Cartesia to Claude, Cursor, ChatGPT & more