How to Use the NVIDIA Audio MCP in OpenAI Agents SDK

Q: How do I configure NVIDIA Audio with OpenAI Agents SDK?

You initialize the connection using MCPServerStreamableHttp with your Vinkius MCP Server endpoint. Pass the server instance into your Agent constructor's mcpservers list. Set cacheToolsList=True to avoid fetching the tool schema on every agent run.

Q: Can I use NVIDIA Audio to clean background noise in OpenAI Agents SDK?

Yes, the cancelnoise tool handles this directly. Your agent calls this tool to strip hums and static from your audio files before sending them to transcription. This saves token costs and improves downstream accuracy.

Q: How does speaker diarization handle multiple voices?

The speakerdiarization tool analyzes the audio file and assigns distinct speaker labels to each segment of speech. Your agent can then structure the transcript chronologically, making it easy to see who spoke when during a call.

Build production-ready voice systems with OpenAI Agents SDK using real-time NVIDIA Audio tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA Audio MCP to OpenAI Agents SDK

Create your Vinkius account to connect NVIDIA Audio to OpenAI Agents SDK 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 NVIDIA Audio with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Clean audio files using OpenAI Agents SDK

The `speech_to_text` tool lets your OpenAI agent transcribe noisy call recordings directly via public URLs. By coupling this with `cancel_noise`, you clean background hums before processing, ensuring your agent doesn't waste tokens on static. This MCP setup runs under the SDK's built-in guardrails. You can validate the output of `cancel_noise` before handing the cleaned text over to your downstream compliance agents.

Safe voice cloning and speech generation

The `clone_voice` tool generates natural speech from a reference audio file, which your OpenAI agent can trigger dynamically. For simpler tasks, `text_to_speech` converts raw text into clear audio using standard voice profiles. Because this runs inside an OpenAI multi-agent system, you can use specialized agent handoffs to verify the generated audio. One agent runs `clone_voice` while a supervisor agent checks the output against your security policies.

Multi-speaker analysis with trace visibility

The `speaker_diarization` tool identifies who said what in multi-party audio files. Your agent uses this MCP tool alongside `summarize_audio` to extract action items from complex customer calls. Every execution of these NVIDIA Audio tools gets logged in your OpenAI dashboard. You see the exact latency of `speaker_diarization` and can debug performance bottlenecks instantly.

Setup guide

Set up NVIDIA Audio 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 NVIDIA Audio tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NVIDIA Audio 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="NVIDIA Audio Agent",
            instructions="You have access to NVIDIA Audio 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 NVIDIA. 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 NVIDIA Audio 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 NVIDIA Audio MCP in OpenAI Agents SDK

You initialize the connection using `MCPServerStreamableHttp` with your Vinkius MCP Server endpoint. Pass the server instance into your Agent constructor's `mcp_servers` list. Set `cacheToolsList=True` to avoid fetching the tool schema on every agent run.

Yes, the `cancel_noise` tool handles this directly. Your agent calls this tool to strip hums and static from your audio files before sending them to transcription. This saves token costs and improves downstream accuracy.

It is secure if you enforce strict agent handoffs. You can build a dedicated supervisor agent that validates the input reference file before calling `clone_voice`. This keeps unauthorized voice generation out of your production pipelines.

The `speaker_diarization` tool analyzes the audio file and assigns distinct speaker labels to each segment of speech. Your agent can then structure the transcript chronologically, making it easy to see who spoke when during a call.

Your raw audio files, voice recordings, and transcripts are processed through Vinkius's secure sandboxed isolates. The data is sent directly to the NVIDIA API for processing and is never stored on Vinkius servers. Ephemeral execution ensures your sensitive customer recordings remain private.

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