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

Get type-safe transcription results in Pydantic AI. No more guessing about your API responses.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-validated transcription for Pydantic AI

Use `init_transcription` to start jobs and rely on Pydantic to validate the output structure at runtime. It stops your agent from crashing due to unexpected response formats. Fetching status with `get_transcription` provides a reliable way to check for completion. You get clean, typed data every time the server returns a result.

Real-time audio streams in Pydantic AI

Connect to live audio using `init_live_session` while keeping your type definitions strict. Your agent receives structured text updates that match your models perfectly. This tool ensures that even live data is validated before your agent acts on it. It keeps your entire pipeline predictable and free from silent errors.

Manage transcription history with Pydantic AI

Track your processed audio files using `list_transcriptions` to keep your records consistent. The tool returns a list that your agent can easily parse into a Pydantic model. Remove stale jobs using `delete_transcription` whenever they are no longer needed. It keeps your storage usage low and your data models focused on current tasks.

Setup guide

Set up Gladia (Speech AI) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "gladia-speech-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Gladia (Speech AI) tools.",
)

result = await agent.run("List recent Gladia (Speech AI) transactions")
print(result.output)

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 Pydantic AI

You use the MCPToolset with the server's HTTP endpoint. Pydantic AI will then automatically validate the responses from the Gladia tools.

Yes, every response is checked against your defined models. If the data doesn't match, the agent catches the error immediately.

It is. Your agent can initiate a live session and process the stream as incoming data. Each chunk is validated against your schema.

The agent will throw a validation error rather than processing bad data. This prevents your system from running with corrupted information.

The server processes your files in a secure, isolated sandbox. It ensures your audio data is handled safely throughout the entire transcription 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