How to Use the Gladia (Speech AI) MCP in Mastra AI

Q: How do I handle failed audio uploads with Gladia (Speech AI) and Mastra AI?

You wrap the uploadaudiofile tool inside a Mastra workflow block configured with automatic retries. If the upload drops, the engine backs off and tries again. This keeps your pipeline running without crashing your agent.

Q: How do I clean up completed audio jobs using Gladia (Speech AI) and Mastra AI?

You configure a workflow step that triggers deletetranscription once your downstream tasks are finished. Mastra's sequential execution guarantees this cleanup tool runs only after your agent successfully extracts the text.

Q: How do I register this MCP Server with a Mastra agent?

Instantiate the MCPClient with your Vinkius URL and spread the tools into your agent's configuration. The framework auto-detects the transport layer and exposes the audio tools to your agent immediately.

Build resilient audio processing workflows with Gladia (Speech AI) and Mastra AI agents.

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 Mastra AI

Create your Vinkius account to connect Gladia (Speech AI) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resilient Audio Pipelines using Mastra AI

Network hiccups shouldn't ruin a transcription run. This MCP Server integrates directly with Mastra's workflow engine, allowing you to wrap `upload_audio_file` in a retry block with exponential backoff. If the initial upload fails due to a spotty connection, the agent automatically retries the operation behind the scenes. This ensures your background transcription pipelines run to completion without manual intervention.

Conditional Audio Routing and Post-Processing

Different audio files require different handling strategies. You can set up conditional branching to check the state of a job via `get_transcription` before deciding the next step in your workflow. If the audio quality is poor, your agent can route the output to a correction step. For successful runs, the workflow proceeds to archive the text and trigger `delete_transcription` to clean up.

Live Session Monitoring with Human-in-the-Loop

Real-time streaming requires tight control over active sessions. This MCP Server allows you to require manual approval before your agent initializes a live WebSocket connection using `init_live_session`. This prevents runaway infrastructure costs from unauthorized live streams. Your team gets a Slack notification to approve the session before any live audio processing begins.

Setup guide

Set up Gladia (Speech AI) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Gladia (Speech AI) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "gladia-speech-ai-mcp-client",
  servers: {
    "gladia-speech-ai-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Gladia (Speech AI) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Gladia (Speech AI) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Gladia (Speech AI) transactions"
);
console.log(result.text);

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 Mastra AI

You wrap the `upload_audio_file` tool inside a Mastra workflow block configured with automatic retries. If the upload drops, the engine backs off and tries again. This keeps your pipeline running without crashing your agent.

Yes, you can spin up real-time streams by registering the MCP Server with your Mastra agent. The agent executes `init_live_session` to open a WebSocket connection. You can then pipe live audio directly to Gladia's processing engine.

You configure a workflow step that triggers `delete_transcription` once your downstream tasks are finished. Mastra's sequential execution guarantees this cleanup tool runs only after your agent successfully extracts the text.

Instantiate the `MCPClient` with your Vinkius URL and spread the tools into your agent's configuration. The framework auto-detects the transport layer and exposes the audio tools to your agent immediately.

Yes, because all traffic passes through an encrypted, zero-trust connection managed by Vinkius. Your audio files and transcripts are never exposed to public internet endpoints or logged on Mastra's servers. You retain full ownership and control over the data lifecycle.

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