How to Use the Coqui TTS (Open Source Speech Studio API) MCP in Google ADK

Q: How do I register Coqui TTS (Open Source Speech Studio API) tools in my Google ADK agent?

Use McpToolset with StreamableHttpServerParameters pointing to your Vinkius endpoint. Pass this toolset into your LlmAgent constructor to expose the voice generation capabilities to Gemini.

Q: How does Gemini use Coqui TTS (Open Source Speech Studio API) to select the right voice?

Gemini reads the tool definition for listmodels to see what voices are available. It then decides which model matches your prompt requirements before calling synthesizespeech.

Q: Can I filter out specific tools on this MCP Server so my Google ADK agent only lists models?

Yes. Use the toolnames parameter in your toolset configuration to only expose listmodels and hide synthesizespeech if you want to restrict write-access.

Bring open-source voice synthesis to Google ADK pipelines with direct access to local and cloud-based Coqui TTS models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coqui TTS (Open Source Speech Studio API) MCP to Google ADK

Create your Vinkius account to connect Coqui TTS (Open Source Speech Studio API) 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 Coqui TTS (Open Source Speech Studio API) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise voice synthesis with Google ADK

Give your Gemini-powered enterprise agents the ability to speak. By exposing this MCP Server to your Google ADK agent, you let Gemini translate complex data directly into spoken audio files. Your agent queries `list_models` to find the right voice, then triggers `synthesize_speech` to output the audio metadata. This lets you build voice interfaces that run on top of your existing Google Cloud infrastructure.

Context-aware speech generation from BigQuery data

Gemini's massive context window lets your agent read thousands of rows of customer data from BigQuery before generating a voice response. The agent processes this data, drafts a personalized script, and sends it to `synthesize_speech`. Because the tool returns metadata about the generated file, your application can immediately play the audio back to the user. No intermediate manual steps or custom API glue required.

Restrict voice tools to specific enterprise agents

You do not always want every agent to have access to voice generation. Google ADK lets you use the `tool_names` filter on your `McpToolset` to expose only what a specific agent needs. You can restrict a billing agent to only use `list_models` for verification, while your notification agent gets full access to `synthesize_speech` to generate outbound audio alerts.

Setup guide

Set up Coqui TTS (Open Source Speech Studio API) 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 Coqui TTS (Open Source Speech Studio API) 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="Coqui TTS (Open Source Speech Studio API)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Coqui TTS (Open Source Speech Studio API) 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 Coqui TTS. 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 Coqui TTS (Open Source Speech Studio API) 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 Coqui TTS (Open Source Speech Studio API) MCP in Google ADK

Use `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius endpoint. Pass this toolset into your `LlmAgent` constructor to expose the voice generation capabilities to Gemini.

Yes. You can connect to the hosted Vinkius server via HTTP, or run it locally using Stdio during development. Both transports support the full `list_models` and `synthesize_speech` toolset.

Gemini reads the tool definition for `list_models` to see what voices are available. It then decides which model matches your prompt requirements before calling `synthesize_speech`.

Yes. Use the `tool_names` parameter in your toolset configuration to only expose `list_models` and hide `synthesize_speech` if you want to restrict write-access.

All text payloads and audio metadata are processed inside an ephemeral, zero-trust V8 sandbox. Your inputs never touch public logs, ensuring enterprise-grade isolation for your voice data.

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