How to Use the Speechnotes MCP in OpenAI Agents SDK

Q: How do I check the status of a job with Speechnotes using OpenAI Agents SDK?

Call gettranscriptionstatus and pass the specific job ID. The agent checks if the transcript is ready, or if it's still processing on the Speechnotes platform. It keeps your workflow moving.

Q: Can I see what languages Speechnotes supports with OpenAI Agents SDK?

Yes. Your agent runs listsupportedlanguages to get a list of all available language codes. This ensures the job payload is correctly configured before starting the transcription.

Q: Does Speechnotes support webhook validation when using OpenAI Agents SDK?

Absolutely. The generatewebhooksignature tool confirms that any incoming data stream truly originated from Speechnotes, preventing spoofed or malicious messages from corrupting your system.

Q: What if I need to delete a job after starting it with Speechnotes using OpenAI Agents SDK?

You use removetranscriptionjob and provide the job ID. This deletes the record from Speechnotes' system, cleaning up unnecessary data entries right away.

Q: How do I handle bulk result exports with Speechnotes using OpenAI Agents SDK?

First, use gettranscriptionexport to determine the best format. Then you can pull all results in that type. The agent makes sure you get a usable file for your downstream processes.

Run full transcription workflows with OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Speechnotes to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Process remote audio files

The `transcribe_audio_url` tool takes a direct URL to an audio file and starts the job. It immediately returns a job ID, letting your agent know the task is running without waiting for the full transcription. Your agent then uses `get_transcription_status` with that job ID. This checks if Speechnotes finished processing or if it needs more time, giving you real-time feedback.

Manage webhooks and payloads

Use the `generate_webhook_signature` tool to validate incoming webhook payloads. Your agent confirms that a notification really came from Speechnotes by verifying its signature. This keeps your production system secure. It's critical for reliability. You can also list what endpoints are ready with `list_configured_webhooks`, making sure your agent knows where the results are going.

Get usage and history data

Need to track costs? Run `get_usage_statistics` to get a breakdown of how much your team used the service. This gives you immediate visibility into consumption patterns. To audit past runs, use `list_transcription_history`. Your agent can pull up details on previous jobs and what they were based on, which is great for debugging.

Setup guide

Set up Speechnotes MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Speechnotes tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Speechnotes tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Speechnotes tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Speechnotes Agent",
            instructions="You have access to Speechnotes tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Call `get_transcription_status` and pass the specific job ID. The agent checks if the transcript is ready, or if it's still processing on the Speechnotes platform. It keeps your workflow moving.

Yes. Your agent runs `list_supported_languages` to get a list of all available language codes. This ensures the job payload is correctly configured before starting the transcription.

Absolutely. The `generate_webhook_signature` tool confirms that any incoming data stream truly originated from Speechnotes, preventing spoofed or malicious messages from corrupting your system.

You use `remove_transcription_job` and provide the job ID. This deletes the record from Speechnotes' system, cleaning up unnecessary data entries right away.

First, use `get_transcription_export` to determine the best format. Then you can pull all results in that type. The agent makes sure you get a usable file for your downstream processes.

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