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

Q: Can a CrewAI agent monitor a live stream using Gladia (Speech AI)?

Yes, a specialized monitoring agent can invoke initlivesession to open a real-time connection. The agent processes the incoming text stream to detect key events or trigger immediate alerts.

Q: How do I set up this MCP Server in a CrewAI codebase?

You pass your Vinkius MCP URL directly into the agent's mcps array parameter. The framework automatically discovers all six Gladia tools and makes them available to the designated agents.

Q: Can I limit which agents have access to delete audio files via the MCP Server?

Yes, you can restrict tool access by using MCPServerHTTP with a tool filter. Only give deletetranscription to your administrator agent while keeping other agents limited to read-only tools.

Coordinate specialized agent teams to transcribe and analyze audio using Gladia (Speech AI) and CrewAI.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Audio Processing with CrewAI

One agent shouldn't have to handle the entire media pipeline alone. This MCP Server lets you divide the labor among a crew of specialized agents working in tandem. Your Uploader Agent handles `upload_audio_file` and hands off the resulting ID to the Transcriber Agent. That agent then runs `init_transcription` and monitors the state until the text is ready.

Autonomous Audio Quality Auditing

Stale or failed jobs can clog up your system. You can assign a Monitor Agent to run `list_transcriptions` periodically to identify stuck or abandoned audio processing tasks. Once identified, the Monitor Agent coordinates with a Cleanup Agent to execute `delete_transcription`. This autonomous loop keeps your storage clean without requiring human database curation.

Real-Time Event Monitoring and Escalation

High-stakes live events require instant coordination. An agent can call `init_live_session` to start monitoring a live stream, looking for specific keywords or distress signals. If a critical keyword is detected, the agent escalates the issue to a human manager. The rest of the crew continues processing the live feed in the background.

Setup guide

Set up Gladia (Speech AI) MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Gladia (Speech AI) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Gladia (Speech AI) Analyst",
    goal="Access and analyze Gladia (Speech AI) data via MCP.",
    backstory="Expert analyst with direct Gladia (Speech AI) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Gladia (Speech AI) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Gladia (Speech AI) Analyst",
        goal="Access and analyze Gladia (Speech AI) data via MCP.",
        backstory="Expert analyst with direct Gladia (Speech AI) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Gladia (Speech AI) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign specific tools to different agents in your crew configuration. For example, give `upload_audio_file` to your ingestion agent and `get_transcription` to your analysis agent. They will pass file IDs and text results among themselves automatically.

Yes, a specialized monitoring agent can invoke `init_live_session` to open a real-time connection. The agent processes the incoming text stream to detect key events or trigger immediate alerts.

You pass your Vinkius MCP URL directly into the agent's `mcps` array parameter. The framework automatically discovers all six Gladia tools and makes them available to the designated agents.

Yes, you can restrict tool access by using `MCPServerHTTP` with a tool filter. Only give `delete_transcription` to your administrator agent while keeping other agents limited to read-only tools.

All operations execute within an isolated, ephemeral V8 sandbox on the Vinkius platform. Your audio files and transcripts are transmitted over TLS-encrypted channels directly to Gladia. No local caching or persistent storage occurs on the agent machines.

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