An astronaut overseeing a futuristic data hub

Connect Deepgram 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. Turn speech into text and text into speech through your agent.

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 · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Deepgram.

  1. 01

    List available models

    This capability provides a directory of all high-performance STT and TTS models available.

  2. 02

    Transcribe audio URL

    This capability converts speech from a provided audio or video URL into text.

  3. 03

    List API keys

    Use this to retrieve identifiers for your active API keys.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Deepgram.

  1. 04

    Get project usage

    Use this to check your current API usage and remaining limits.

  2. 05

    List deepgram projects

    This capability returns a list of all your Deepgram projects.

  3. 06

    Convert text to speech

    This capability generates audio files from your text input using neural speech synthesis.

Real work

What teams actually run

01

Meeting Transcription

An engineer provides a recording URL to get a formatted transcript with speaker labels.

02

Voiceover Generation

A creator turns written scripts into audio files using the Aura engine.

03

API Monitoring

A developer asks their agent to check how many minutes of transcription they have left.

04

Project Management

A team lead uses the agent to list all active projects and API keys.

Automate a task

Put Deepgram 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

Deepgram 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.

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

You don't need a client to put Deepgram 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

794ms average. Fast in production.

Deepgram is checked daily against the live service.

Daily averagePeak 1051ms
Oct 5Today
Fastest day
697ms
Slowest day
1051ms
14-day trend
Stable-1%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 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 Deepgram, so you can see the experience inside your AI.

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

Deepgram Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_TncgUjBvIqBaRxaOCzAMTEFPrPacCVhmUvpvUOyU/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 — Deepgram capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "deepgram-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_TncgUjBvIqBaRxaOCzAMTEFPrPacCVhmUvpvUOyU/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 Deepgram in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Deepgram owners hand off.

This MCP is built for professionals who need to automate audio workflows through a conversational interface.

  • 01

    Developers

    They hand off transcription and TTS integration tasks to their agent.

  • 02

    Content Creators

    They use the agent to automate voiceovers and subtitles for video assets.

  • 03

    Research Teams

    They delegate the processing of interview recordings and usage monitoring to the agent.

FAQ

Questions Deepgram owners ask.

  • 01

    How do I connect Deepgram to my AI client?

    You subscribe to the MCP on Vinkius and then connect your client like Claude or Cursor. You will need to provide your Deepgram API key during setup.

  • 02

    Can I transcribe audio from a link?

    Yes. You can use the transcribe_audio_url capability to convert speech from public audio or video URLs into text.

  • 03

    What models does this MCP use?

    The MCP provides access to Deepgram's high-performance models, including Nova-3 for transcription and the Aura engine for speech synthesis.

  • 04

    Can I check my API usage through my agent?

    Yes. You can use the get_project_usage capability to check your API utilization and minute consumption.

  • 05

    Does this support speaker diarization?

    Yes. The transcription capabilities include smart formatting and diarization to identify different speakers.

  • 06

    How do I get a Deepgram API Key?

    Log in to the Deepgram Console, navigate to the API Keys section, and create a new key with the necessary permissions.

  • 07

    What is the Nova-3 model?

    Nova-3 is Deepgram's latest state-of-the-art transcription model, offering unmatched speed and accuracy for real-world audio.

  • 08

    Can I synthesize speech in different voices?

    Yes! The convert_text_to_speech capability allows you to specify models like aura-asteria-en or aura-orion-en for different vocal profiles.

Connect Deepgram to Claude, Cursor, ChatGPT & more