How to Use the Deepgram MCP in Vercel AI SDK

Q: How do I handle Deepgram audio streaming errors in Vercel AI SDK?

You wrap the transcribeurl call in the SDK's standard error boundaries to catch network hiccups instantly. Since the MCP connection handles the raw socket layer, your frontend code only has to deal with standard TypeScript exceptions.

Q: Can I use Deepgram text-to-speech with Vercel AI SDK streamText?

Yes, you can feed the output chunks of streamText directly into the speaktext tool. This allows you to generate audio files as the SDK receives text from your LLM provider.

Stream live audio transcripts and voice synthesis directly into your Next.js frontend using the Deepgram MCP Server with Vercel AI SDK.

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

Stream transcripts directly to Vercel AI SDK UIs

Your Next.js interface shouldn't freeze while Vercel AI SDK waits for a massive Deepgram audio transcript. When you hook up the `transcribe_url` tool to your Vercel AI SDK setup, you feed remote audio files to Deepgram and pipe the resulting text straight to the screen. The Vercel AI SDK handles the streaming UI components while the Deepgram MCP Server manages the underlying API handshakes. This setup keeps your Vercel AI SDK Edge Functions fast because the heavy audio transcription happens on Deepgram's infrastructure. Your Next.js frontend grabs the incoming text chunks as Deepgram spits them out through the Vercel AI SDK interface.

Generate speech inside Vercel AI SDK edge routes

Turn raw text responses into spoken audio on the fly using the Deepgram `speak_text` tool within your Vercel AI SDK application. Your Vercel AI SDK code can trigger Deepgram audio generation the moment your text model finishes its thought. By running this through the Deepgram MCP Server, you avoid bundling bulky audio SDKs into your Vercel AI SDK client bundle. The Vinkius server handles the Deepgram authentication and returns the raw audio data directly to your streaming Vercel AI SDK frontend.

Track Deepgram balances in Vercel AI SDK dashboards

Build internal Next.js admin panels that monitor your Deepgram audio expenses in real-time using Vercel AI SDK with `get_balances` and `get_usage`. Your support agents can check current Deepgram usage limits or project states directly inside the Vercel AI SDK chat interface. You can let senior admins generate temporary credentials using the Deepgram `create_key` tool right inside your Vercel AI SDK app. The Vercel AI SDK renders the newly minted Deepgram API keys securely, keeping your backend master credentials hidden from the browser.

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 wrap the `transcribe_url` call in the SDK's standard error boundaries to catch network hiccups instantly. Since the MCP connection handles the raw socket layer, your frontend code only has to deal with standard TypeScript exceptions.

Yes, you can feed the output chunks of `streamText` directly into the `speak_text` tool. This allows you to generate audio files as the SDK receives text from your LLM provider.

The MCP Server runs in a secure V8 sandbox on Vinkius, meaning your Deepgram master keys are never exposed to the client-side Vercel AI SDK environment. The SDK only receives the final audio or text payload, not the credentials.

Yes, it is fully compatible. The TypeScript client connects to Vinkius via lightweight HTTP transports, bypassing Node-specific dependencies so your Vercel AI SDK edge routes run without cold starts.

Your Deepgram API keys, account balances, and audio files are processed in ephemeral, zero-trust V8 isolates. Vinkius never caches your raw transcripts or key payloads, passing them securely between your Vercel AI SDK serverless functions and Deepgram's endpoints.

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