SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Gladia MCP with Autogen

Connect Autogen to Gladia MCP. Transcribe this recorded meeting audio file, start real-time transcription from your microphone, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Gladia logoGladia
Api Key

Gladia delivers fast, accurate audio transcription and intelligence via a simple API. Instantly turn speech into actionable data for smarter workflows.

9 Tools

Introduction

This guide walks you through connecting Gladia to AutoGen using the Composio tool router. By the end, you'll have a working Gladia agent that can transcribe pre-recorded audio and video, start live transcription sessions, upload media files, and fetch transcription results through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Gladia account through Composio's Gladia MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Gladia with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Gladia
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Gladia tools
  • Run a live chat loop where you ask the agent to perform Gladia operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

What is the Gladia MCP server, and what's possible with it?

The Gladia MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Gladia account. It provides structured and secure access to advanced audio transcription and intelligence services, so your agent can perform actions like uploading audio, transcribing recordings, retrieving live transcription results, and organizing jobs on your behalf.

  • Real-time and asynchronous transcription: Instantly start live or pre-recorded transcription jobs for audio and video files, letting your agent process spoken content with ease.
  • Audio and video file uploads: Seamlessly upload audio or video files to Gladia's servers as a first step before transcription or analysis.
  • Fetch detailed transcription results: Retrieve comprehensive results and metadata from both live and pre-recorded transcription sessions, including job status and transcribed text.
  • Job management and status tracking: List, filter, and monitor all your live and pre-recorded transcription jobs so your agent can keep tabs on ongoing or completed work.
  • Effortless workflow automation: Combine audio file handling, job initiation, and result retrieval into streamlined, agent-driven automations—saving you time and manual effort.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Gladia account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Gladia via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Gladia connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Gladia session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["gladia"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Gladia tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Gladia assistant agent with MCP tools
    agent = AssistantAgent(
        name="gladia_assistant",
        description="An AI assistant that helps with Gladia operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Gladia tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Gladia related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Gladia tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Gladia and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Gladia session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["gladia"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Gladia assistant agent with MCP tools
        agent = AssistantAgent(
            name="gladia_assistant",
            description="An AI assistant that helps with Gladia operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Gladia related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Gladia through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Gladia, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Gladia action and event your agent gets out of the box.

Delete Live Session

Tool to delete a live transcription session and all its associated data (audio file, transcription).

Delete Pre-recorded Job

Tool to delete a pre-recorded transcription job and all its associated data (audio file, transcription).

Get live transcription result

Tool to retrieve metadata and results of a live transcription job.

Get Pre-recorded Job

Tool to retrieve a pre-recorded transcription job's metadata, status, and results by ID.

Initiate Live Transcription Session

Initiates a live (real-time) transcription session with Gladia's API.

Initiate Pre-Recorded Transcription

Tool to initiate a pre-recorded transcription job.

List live transcription jobs

Tool to list live transcription jobs.

List Pre-Recorded Jobs

Tool to list all pre-recorded transcription jobs matching the query parameters.

Upload Audio/Video File

Upload an audio or video file to Gladia for speech-to-text transcription.

FRAMEWORKS

How to build Gladia MCP Agent with another framework

Claude Code logo

Claude Code

Use Gladia MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Gladia MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Gladia MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Gladia MCP with Claude Agent SDK

Codex logo

Codex

Use Gladia MCP with Codex

OpenClaw logo

OpenClaw

Use Gladia MCP with OpenClaw

Hermes logo

Hermes

Use Gladia MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Gladia MCP with Atomic Agent

Google ADK logo

Google ADK

Use Gladia MCP with Google ADK

LangChain logo

LangChain

Use Gladia MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Gladia MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Gladia MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Gladia MCP with LlamaIndex

CrewAI logo

CrewAI

Use Gladia MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Gladia MCP with Pydantic AI

FAQ

Frequently asked questions

Start with Gladia.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Gladia tool your agent needs.Free to start.

Start building