How to Use the Gladia (Speech AI) MCP in Vercel AI SDK

Q: How do I handle live audio streaming with Gladia (Speech AI) and the Vercel AI SDK?

You initialize a WebSocket connection by calling initlivesession through the SDK's tool calling interface. This feeds the live audio stream directly into your React or Next.js frontend components. The text renders on the screen in real-time as the audio is processed.

Q: What is the cleanest setup for Gladia (Speech AI) with the Vercel AI SDK?

Install the @ai-sdk/mcp package and create an MCP client pointing to your Vinkius endpoint. Pass the tools directly into streamText and remember to call mcpClient.close() once the session ends to prevent memory leaks.

Q: How do I list previous audio jobs in my web app?

Your agent invokes listtranscriptions to retrieve all past runs. You can map this array directly to a React state variable to render a clean history log for your users.

Stream real-time Gladia (Speech AI) transcripts directly into your Next.js UI using the 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 Gladia (Speech AI) MCP to Vercel AI SDK

Create your Vinkius account to connect Gladia (Speech AI) 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 Gladia (Speech AI) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Audio Transcripts via Vercel AI SDK

Frontends shouldn't freeze while waiting for giant audio payloads to process. Connecting this MCP Server to your Edge Functions lets you spin up `init_live_session` instantly, pushing raw audio text directly to your users' screens as it happens. You bypass the typical lag of polling database states. By feeding the live stream directly into your UI components, your users watch the words materialize word-by-word without staring at a loading spinner.

Batch Audio Processing Without Server Overhead

Handling massive media uploads usually breaks serverless timeout limits. Solve this by triggering `upload_audio_file` via our MCP Server directly from your client-side application state to secure a direct-to-cloud pipeline. Once the file lands, your agent fires off `init_transcription` to kick off the background job. You can then poll the status using `get_transcription` to update your React state dynamically when the output is ready.

Clean Up Audio Workspace Resources

Storing endless audio logs on third-party servers raises compliance red flags. Keep your storage footprint tight by letting your AI client execute `delete_transcription` the moment your user confirms they are done with the session. Your agent can fetch the active list via `list_transcriptions` to show users what files are currently hosted. This gives users full control over their audio data directly from your custom web dashboard.

Setup guide

Set up Gladia (Speech AI) 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 Gladia (Speech AI) 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 Gladia (Speech AI) 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 Gladia. 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 Gladia (Speech AI) 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 Gladia (Speech AI) MCP in Vercel AI SDK

You initialize a WebSocket connection by calling `init_live_session` through the SDK's tool calling interface. This feeds the live audio stream directly into your React or Next.js frontend components. The text renders on the screen in real-time as the audio is processed.

Yes, you can run these background jobs without hitting serverless timeout limits. By calling `upload_audio_file` and starting the job with `init_transcription`, the heavy lifting happens on Gladia's servers. Your Edge Function simply monitors the job and streams the final text back.

Install the `@ai-sdk/mcp` package and create an MCP client pointing to your Vinkius endpoint. Pass the tools directly into `streamText` and remember to call `mcpClient.close()` once the session ends to prevent memory leaks.

Your agent invokes `list_transcriptions` to retrieve all past runs. You can map this array directly to a React state variable to render a clean history log for your users.

Your raw audio files and transcripts are processed in a secure, ephemeral V8 isolate sandbox on Vinkius before hitting Gladia. No data is cached or stored on intermediate servers during transit. Once you run `delete_transcription`, the records are wiped permanently.

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