How to Use the Hugging Face Audio MCP in Google ADK

Q: Can Google ADK filter which Hugging Face Audio tools are exposed?

You can restrict access using the toolnames parameter. If you only want your agent to use transcribeaudio, just pass that specific name when configuring the MCP Server.

Bring Hugging Face Audio into your Google ADK pipelines to process massive audio datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hugging Face Audio MCP to Google ADK

Create your Vinkius account to connect Hugging Face 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 Hugging Face Audio with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Transcribe long-form audio via MCP Server

`transcribe_audio` pulls speech from audio files and converts it to text. When paired with Gemini's massive 1M+ token context window, you can transcribe hours of audio and feed the entire transcript directly into your prompt. Your Google ADK agent pulls the audio URL, runs the transcription tool, and writes the output straight to BigQuery. You get structured text data from messy audio files without leaving your Google Cloud infrastructure.

Filter and classify raw sound files

`classify_audio` identifies specific sounds in an audio file provided via URL. If you are processing field recordings, your agent knows immediately whether it is listening to machinery, nature, or human speech. If the audio is too noisy, the agent can trigger `enhance_audio` to strip out the background interference. This gives Vertex AI cleaner data to work with when running downstream analytics.

Generate spoken responses

`text_to_speech` takes text strings and outputs Base64 encoded audio. You feed it a script, and it hands back a ready-to-play voice file. You expose this tool to your LlmAgent using the McpToolset wrapper. The agent handles the back-and-forth, deciding when to speak a response versus when to just log the text.

Setup guide

Set up Hugging Face 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 Hugging Face 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="Hugging Face Audio_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Hugging Face 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 Hugging Face Audio. 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 Hugging Face 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 Hugging Face Audio MCP in Google ADK

Install the google-adk package. Wrap your endpoint in StreamableHttpServerParameters and pass it to McpToolset, then assign that toolset to your LlmAgent.

You can restrict access using the tool_names parameter. If you only want your agent to use transcribe_audio, just pass that specific name when configuring the MCP Server.

The tools process the audio URLs you provide. Your Google ADK agent can read URLs from BigQuery, run them through the MCP Server, and write the resulting text back to your database.

The tools expect a URL for the audio file. You need to upload your local files to Google Cloud Storage first and pass the public or signed URLs to the tools.

The raw WAV files and Base64 payloads route through a zero-trust architecture. The Vinkius platform authenticates via a single endpoint token and processes the audio ephemerally, meaning your Vertex AI training data never leaks.

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