How to Use the NVIDIA Audio MCP in Google ADK

Q: How do I connect NVIDIA Audio to Google ADK?

You use McpToolset with your Vinkius MCP Server endpoint and pass it to your LlmAgent tools list. This exposes the entire suite of audio processing tools to your Gemini models. You can also use the toolnames filter to restrict access if needed.

Q: Can Google ADK run NVIDIA Audio tools in parallel?

Yes, your agent can trigger multiple tool calls like speechtotext and speakerdiarization concurrently. This is highly efficient when processing batches of customer call recordings stored in Google Cloud Storage.

Q: How do I store NVIDIA Audio transcripts in BigQuery using Google ADK?

Your Google ADK agent calls speechtotext to generate the transcript, then runs summarizeaudio to extract key points. The agent can then use Google Cloud integrations to write the structured output directly to your BigQuery datasets.

Q: Can I limit which NVIDIA Audio tools are exposed?

Yes, you can use the toolnames parameter in your McpToolset configuration. This MCP configuration lets you expose only specific tools like cancelnoise while hiding sensitive ones like clonevoice from the agent.

Run NVIDIA Audio tools directly from your Google ADK enterprise agents to process high-volume audio.

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 Google ADK

Create your Vinkius account to connect NVIDIA Audio to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process massive audio files with Google ADK

The `speech_to_text` tool transcribes long-form audio files and feeds them directly into Gemini's massive context window. Since Google ADK handles 1M+ tokens, your agent can analyze hours of raw audio in a single run. Once transcribed, the `summarize_audio` tool extracts key themes from the meeting. You can then write these summaries directly into BigQuery tables for long-term storage and analytical queries.

Clean and classify audio files at scale

The `cancel_noise` tool strips background interference from customer calls before your Google ADK agent processes them. After cleaning, the `classify_audio` tool categorizes background sounds like sirens or keyboard clicks with confidence scores. This gives your agent deep context about the caller's environment. You can use this metadata to route urgent calls or flag potential security issues in your Vertex AI pipeline.

Translate and punctuate conversations

The `audio_translation` tool translates spoken audio directly into your target language. Your Google ADK agent can then run `punctuate_text` to fix capitalization and formatting on the raw translation. This MCP toolset is perfect for processing international support calls. The agent cleans up the transcript, matches it with customer records in BigQuery, and translates the response back using `text_to_speech`.

Setup guide

Set up NVIDIA Audio MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with NVIDIA Audio tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="NVIDIA Audio_agent",
    model="gemini-2.0-flash",
    instruction="You have access to NVIDIA Audio tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You use `McpToolset` with your Vinkius MCP Server endpoint and pass it to your `LlmAgent` tools list. This exposes the entire suite of audio processing tools to your Gemini models. You can also use the `tool_names` filter to restrict access if needed.

Yes, your agent can trigger multiple tool calls like `speech_to_text` and `speaker_diarization` concurrently. This is highly efficient when processing batches of customer call recordings stored in Google Cloud Storage.

Your Google ADK agent calls `speech_to_text` to generate the transcript, then runs `summarize_audio` to extract key points. The agent can then use Google Cloud integrations to write the structured output directly to your BigQuery datasets.

Yes, you can use the `tool_names` parameter in your `McpToolset` configuration. This MCP configuration lets you expose only specific tools like `cancel_noise` while hiding sensitive ones like `clone_voice` from the agent.

This MCP setup processes your audio files and voice recordings through ephemeral V8 isolates. No audio data or transcribed text is logged or stored on the Vinkius platform. All connections are secured via token authentication, keeping your enterprise communication safe.

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