How to Use the Speechnotes MCP in LangChain

Q: Can I track usage with Speechnotes when using LangChain?

Yes. You can call getusagestatistics via the MCP Server to pull detailed logs showing how many transcripts you've run and what models were used. This gives full observability into your entire workflow.

Q: What is the best way to export data from Speechnotes in a LangChain application?

Use gettranscriptionexport after confirming the job status with gettranscriptionstatus. This function handles formatting the final transcript text into an output that's easy for subsequent steps in your chain to consume.

Q: How do I verify a webhook payload from Speechnotes using LangChain?

You use generatewebhooksignature to confirm the incoming data is legitimate. This signature check makes sure that any notification or status update you receive really came from Speechnotes and wasn't tampered with.

Build complex, multi-step pipelines with Speechnotes and LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Speechnotes MCP to LangChain

Create your Vinkius account to connect Speechnotes to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Speechnotes with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Transcribing Audio Files with the MCP Server

Start by calling `transcribe_audio_url` to process a remote file. This function initiates the job, giving you an immediate Job ID. After initiation, your agent needs confirmation that the transcription is finished. You can check progress using `get_transcription_status`. This ensures your multi-step chain doesn't proceed until the data is ready for use.

Managing Credentials and Outputs in LangChain

You should always verify connection health first. Run `test_speechnotes_auth` to confirm your API client can reach the Speechnotes platform. If successful, you'll know that subsequent steps involving data retrieval will work. When the job is done, don't just read the raw text. Use `get_transcription_export` to pull the results in a format (like JSON or CSV) optimized for the next step in your chain.

Controlling Job Flow and Usage Tracking

Sometimes, you need to clean up after yourself. If an old job is no longer relevant, call `remove_transcription_job` using its ID. This keeps your system tidy and prevents unnecessary data clutter. Keep track of costs by running `get_remaining_credits`. Your agent can build a flow that checks credits before initiating expensive calls, making the entire process predictable for the user.

Setup guide

Set up Speechnotes 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 Speechnotes 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({
    "speechnotes-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 Speechnotes 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 Speechnotes. 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 Speechnotes 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 Speechnotes MCP in LangChain

Your AI client treats each tool as an atomic step in a reasoning graph. The output of one call (like a Job ID) becomes the direct input for the next tool, allowing you to build complex, multi-stage pipelines using both Speechnotes and LangChain.

Yes. You can call `get_usage_statistics` via the MCP Server to pull detailed logs showing how many transcripts you've run and what models were used. This gives full observability into your entire workflow.

Use `get_transcription_export` after confirming the job status with `get_transcription_status`. This function handles formatting the final transcript text into an output that's easy for subsequent steps in your chain to consume.

You use `generate_webhook_signature` to confirm the incoming data is legitimate. This signature check makes sure that any notification or status update you receive really came from Speechnotes and wasn't tampered with.

This server handles audio files, job records, and usage statistics. Since your agent interacts directly with the remote file URL via `transcribe_audio_url`, you're dealing with sensitive input media.

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