An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Deepgram (Alternative) 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 via natural conversation.

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 lets your agent see the full directory of high-performance STT and TTS models available in your account.

  2. 02

    Convert text to speech

    Your agent uses this to generate natural sounding audio files from text input using the Aura engine.

  3. 03

    Get project usage

    This capability provides real-time data on your API utilization, minute consumption, and request counts.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Deepgram.

  1. 04

    List API keys

    Use this to retrieve identifiers for your active API keys to maintain security oversight.

  2. 05

    List deepgram projects

    This capability pulls a list of all your Deepgram projects for easy organization.

  3. 06

    Transcribe audio URL

    Your agent calls this to convert audio files located at a public URL into high-fidelity text.

Real work

What teams actually run

01

Automated Meeting Minutes

Provide a recording URL and have your agent generate a formatted transcript with speaker labels.

02

Voiceover Generation

Turn written scripts into natural speech files for video production.

03

Usage Auditing

Ask your agent to check how many minutes of audio you have consumed this month.

04

Model Selection

Query your agent to find the specific model that meets your latency or accuracy requirements.

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.

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 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

956ms average. Fast in production.

Deepgram is checked daily against the live service.

Daily averagePeak 1347ms
Oct 3Today
Fastest day
656ms
Slowest day
1347ms
14-day trend
Slowing+37%

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_b4nB7qQlpNhKdRs2pTzPWFY3jI1pKu8WFxapjmwu/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-alternative-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_b4nB7qQlpNhKdRs2pTzPWFY3jI1pKu8WFxapjmwu/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 anyone who needs to automate audio processing without touching a web dashboard.

  • 01

    Developers

    They use it to automate meeting transcriptions and add voice to apps via natural language.

  • 02

    Content Creators

    They automate voiceovers and subtitles for video assets directly in their workspace.

  • 03

    Research Teams

    They scale the processing of interview recordings and monitor usage through AI queries.

FAQ

Questions Deepgram owners ask.

  • 01

    How do I connect Deepgram to my AI client?

    You subscribe to the MCP on Vinkius and provide your Deepgram API key. Once connected, you can use it in any compatible client like Claude or Cursor.

  • 02

    Can I transcribe audio files directly?

    Yes, you can provide a public URL for an audio file, and the agent will use the transcription capabilities to convert it to text.

  • 03

    What models does this MCP use?

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

  • 04

    Can I monitor my API costs through the AI?

    Yes, you can ask your agent to check project usage, minute consumption, and request counts.

  • 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.

Explore

More in AI Frontier

Suggestions

Connect Deepgram to Claude, Cursor, ChatGPT & more