How to Use the Deepgram MCP in Vercel AI SDK

Q: How do I transcribe audio with Deepgram and the Vercel AI SDK?

You pass the transcribeaudiourl tool to the streamText function. The Vercel AI SDK will automatically handle streaming the transcript text into your UI as it's generated by Deepgram.

Q: Can I see a list of available Deepgram models with the Vercel AI SDK?

Yes. The listavailablemodels tool is included. Your agent can call it to get a list of all the transcription and speech models you can use for other tasks.

Q: How does this Deepgram MCP Server connect to my Vercel AI SDK project?

You instantiate createMCPClient with the Vinkius endpoint URL. Then you pass the tools from mcpClient.tools() into the AI SDK's generateText or streamText functions. It's built to work directly with the SDK's tool-calling system.

Q: Is it possible to check my Deepgram API usage from my Vercel AI SDK app?

Absolutely. Just have your agent use the getprojectusage tool. It returns your current API usage stats, which you can then display anywhere in your frontend.

Stream Deepgram transcriptions and audio right into your UI. With the Vercel AI SDK, you can show results character-by-character, not after a spinner.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deepgram MCP to Vercel AI SDK

Create your Vinkius account to connect Deepgram to Vercel AI SDK 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 Deepgram with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Audio Transcription in Your UI

This MCP Server gives your agent the `transcribe_audio_url` tool. When you use it with the Vercel AI SDK, the transcript doesn't just pop in at the end. It streams directly into your React or Next.js components, word by word. You can build an interface where users see the transcription happen live. It's a much better experience than staring at a loading animation. Your frontend gets the data as Deepgram processes it, and the AI SDK makes it simple to render those partial results.

Generate Speech On-Demand

The `convert_text_to_speech` tool lets your application talk. Just pass text to your agent, and it generates audio using one of Deepgram's models. Combined with the Vercel AI SDK, you can build responsive frontends that provide audio feedback. For example, your agent could read a summary aloud after processing a document. You get a URL to the generated audio file back, ready to play in the browser.

Build Dashboards with the Vercel AI SDK

Give your agent tools to manage your Deepgram account. You can use `list_deepgram_projects` to get a list of your projects or `get_project_usage` to check your API credit balance. This is perfect for building internal dashboards or account pages directly in your app. Your agent can fetch the data, and you can display it in a clean UI. You can even use `list_api_keys` to check on your active credentials without leaving your application.

Setup guide

Set up Deepgram MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Deepgram tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Deepgram transactions",
});

console.log(text);
await mcpClient.close();

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 Deepgram. 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 Deepgram 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 Deepgram MCP in Vercel AI SDK

You pass the `transcribe_audio_url` tool to the `streamText` function. The Vercel AI SDK will automatically handle streaming the transcript text into your UI as it's generated by Deepgram.

Yes. The `list_available_models` tool is included. Your agent can call it to get a list of all the transcription and speech models you can use for other tasks.

You instantiate `createMCPClient` with the Vinkius endpoint URL. Then you pass the tools from `mcpClient.tools()` into the AI SDK's `generateText` or `streamText` functions. It's built to work directly with the SDK's tool-calling system.

Absolutely. Just have your agent use the `get_project_usage` tool. It returns your current API usage stats, which you can then display anywhere in your frontend.

The server processes audio file URLs for transcription and text strings for speech generation. Each request runs in a zero-trust, ephemeral sandbox on Vinkius. We don't log or store the content of your requests to Deepgram.

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