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

Q: How do I start a batch transcription using Gladia (Speech AI) in LangChain?

Use uploadaudiofile to send your file, then pass the file URL to inittranscription. Your LangChain agent can track the progress using gettranscription until the text is ready.

Q: Can my LangChain agent handle live streaming with Gladia (Speech AI)?

Yes. You initialize the streaming WebSocket using initlivesession. This MCP tool returns the endpoint details your agent needs to handle live audio feeds.

Q: How do I list past speech-to-text jobs in LangChain?

Call listtranscriptions to retrieve your history. Your agent can parse this list to find specific past sessions without starting new jobs.

Q: What is the best way to handle large audio files?

Upload them first using uploadaudiofile. Once the upload completes, pass the payload directly to your next chain step to start processing.

Feed audio directly into your LangChain chains and let your agents handle transcription via this MCP Server.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain audio uploads with LangChain agents

`upload_audio_file` sends raw audio files directly from your workspace to Gladia's servers. Your LangChain agent handles the file transfer first, then immediately grabs the file token to kick off the next step in your chain. This means your LangChain chain bypasses manual audio file handling completely. By feeding the resulting token into `init_transcription`, your agent initiates the background batch process without requiring manual API coordination.

Real-time speech pipelines via this MCP Server

`init_live_session` spins up a live WebSocket channel so your agent can process streaming voice data on the fly. This MCP tool sets up the connection parameters so your LangChain pipeline can ingest live audio feeds. LangSmith traces every step of this live interaction, showing you exactly when the connection starts and how your agent responds to incoming text blocks. You get clear visibility into LangChain speech pipeline latency bottlenecks without guessing.

Clean up stale transcriptions automatically

`delete_transcription` removes processed data from Gladia's servers once your LangChain agent finishes extracting insights. Keeping your Gladia cloud storage clean becomes a simple final step in your LangChain run. The agent checks the status using `get_transcription` before triggering the deletion. Once the transcribed text matches your LangChain validation rules, the cleanup tool runs automatically to protect data hygiene.

Setup guide

Set up Gladia (Speech AI) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Gladia (Speech AI) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "gladia-speech-ai-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Gladia (Speech AI) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Use `upload_audio_file` to send your file, then pass the file URL to `init_transcription`. Your LangChain agent can track the progress using `get_transcription` until the text is ready.

Yes. You initialize the streaming WebSocket using `init_live_session`. This MCP tool returns the endpoint details your agent needs to handle live audio feeds.

Call `list_transcriptions` to retrieve your history. Your agent can parse this list to find specific past sessions without starting new jobs.

Upload them first using `upload_audio_file`. Once the upload completes, pass the payload directly to your next chain step to start processing.

Your raw audio files and text transcripts are processed in Vinkius's zero-trust V8 sandbox via the MCP pipeline. All authorization tokens are managed securely, meaning your LangChain client never exposes API keys to external environments.

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