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

Q: Can my OpenAI Agents SDK agent use Gladia (Speech AI) to transcribe files?

Yes, the agent uses uploadaudiofile to send the file to the server and inittranscription to start the job. It treats the transcription process as a standard tool call.

Q: Does the OpenAI Agents SDK support real-time audio with Gladia (Speech AI)?

It does. You use the initlivesession tool to open a WebSocket connection for continuous audio processing. Your agent handles the live stream results as they arrive.

Get accurate speech-to-text directly in your OpenAI Agents SDK workflow. Stop wasting time on manual audio processing.

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 OpenAI Agents SDK

Create your Vinkius account to connect Gladia (Speech AI) to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Full transcription control for OpenAI Agents SDK

Your agent can trigger `init_transcription` to process long-form audio files without breaking its current flow. Just pass the file and let the server handle the heavy lifting while your agent focuses on the next task. Use `get_transcription` to poll for results once the job finishes. It keeps your agent's state clean and ensures you only deal with finalized text data.

Real-time audio streaming for your agent

Connect your live audio feeds using `init_live_session` so your agent reacts to conversations as they happen. It removes the latency of waiting for a file upload to complete. This tool is built for agents that need to stay in the loop during customer calls. Your agent stays responsive while the raw audio stream is converted into actionable text.

Manage your audio history in OpenAI Agents SDK

Keep track of past jobs using `list_transcriptions` to see what your agent has already processed. It saves you from re-running expensive jobs on the same files. If you need to clear out old data, `delete_transcription` removes the records from the server. It keeps your workspace tidy and ensures your agent is only working with relevant information.

Setup guide

Set up Gladia (Speech AI) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Gladia (Speech AI) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Gladia (Speech AI) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Gladia (Speech AI) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Gladia (Speech AI) Agent",
            instructions="You have access to Gladia (Speech AI) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You initialize the connection using the MCPServerStreamableHttp class. Just point it at the server URL and pass it into your agent's tool configuration.

Yes, the agent uses `upload_audio_file` to send the file to the server and `init_transcription` to start the job. It treats the transcription process as a standard tool call.

It does. You use the `init_live_session` tool to open a WebSocket connection for continuous audio processing. Your agent handles the live stream results as they arrive.

The server returns the processed text directly to the agent's context once the job completes. You can then trigger follow-up actions based on that text.

Your audio files are processed in a secure environment and are not stored indefinitely. The server only keeps them long enough to complete the transcription job.

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