How to Use the LMNT (Ultra-low Latency Speech Synthesis) MCP in OpenAI Agents SDK

Q: How do I connect LMNT (Ultra-low Latency Speech Synthesis) to my OpenAI Agents SDK pipeline?

Install the package with pip install openai-agents and initialize the server using MCPServerStreamableHttp. Pass the server object into your Agent constructor within the mcpservers list. The SDK automatically discovers all seven speech tools.

Q: How does this MCP Server handle high-throughput audio generation?

The generatespeech tool returns raw base64 data directly to the client. By enabling cacheToolsList=True, you remove discovery latency, ensuring the agent triggers the synthesis tool instantly on every turn.

Q: What is the best way to manage voice profiles dynamically?

Your agent uses listvoices to inspect available profiles and updatevoice to modify their metadata. The OpenAI Agents SDK lets you coordinate these actions across specialized agents, handing off tasks when a voice change is needed.

Get raw audio back in milliseconds by wire-framing OpenAI Agents SDK directly to your voice assets via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LMNT (Ultra-low Latency Speech Synthesis) MCP to OpenAI Agents SDK

Create your Vinkius account to connect LMNT (Ultra-low Latency Speech Synthesis) 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 LMNT (Ultra-low Latency Speech Synthesis) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time speech synthesis with OpenAI Agents SDK

The `generate_speech` tool converts text strings into base64 encoded audio files instantly. Your agent calls this endpoint during live chat runs, receiving audio packets back before the user notices a pause. By setting `cacheToolsList=True` in your Python configuration, the SDK bypasses discovery overhead on subsequent turns. This direct pipeline prevents conversational lag in production. Because the OpenAI Agents SDK manages state across execution steps, your agent tracks the generated audio payloads and passes them to your frontend audio player without manual glue code.

Instant voice cloning under strict SDK guardrails

The `create_voice` tool clones custom voices from short audio samples directly within your agent flows. Safety is handled by the SDK's built-in guardrails, which validate voice creation parameters before executing the API request. You write rules that prevent the agent from cloning unauthorized voices or executing unapproved requests. Once verified, the agent retrieves the new voice ID using `get_voice` to update its active voice profile. This keeps your custom voice directory clean and prevents your application from running up unexpected usage bills.

Trace voice operations on the OpenAI dashboard

The `list_voices` tool fetches your entire custom voice library so your agent can select the right tone for the current user. When using this MCP Server, every API call is logged inside the OpenAI tracing dashboard. You see exactly when the agent requested a voice list or modified a voice profile via `update_voice`. If an agent attempts to call `delete_voice` by mistake, the SDK's tracing and validation layer catches the error before the voice is lost. You get full visibility into the agent's decision-making process, making debugging production audio workflows simple.

Setup guide

Set up LMNT (Ultra-low Latency Speech Synthesis) 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 LMNT (Ultra-low Latency Speech Synthesis) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LMNT (Ultra-low Latency Speech Synthesis) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LMNT (Ultra-low Latency Speech Synthesis) 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="LMNT (Ultra-low Latency Speech Synthesis) Agent",
            instructions="You have access to LMNT (Ultra-low Latency Speech Synthesis) 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 LMNT. 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 LMNT (Ultra-low Latency Speech Synthesis) 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 LMNT (Ultra-low Latency Speech Synthesis) MCP in OpenAI Agents SDK

Install the package with `pip install openai-agents` and initialize the server using `MCPServerStreamableHttp`. Pass the server object into your Agent constructor within the `mcp_servers` list. The SDK automatically discovers all seven speech tools.

Yes, the SDK enforces strict validation rules before invoking `create_voice`. You can write custom guardrails that inspect the input files before the agent triggers the cloning process.

The `generate_speech` tool returns raw base64 data directly to the client. By enabling `cacheToolsList=True`, you remove discovery latency, ensuring the agent triggers the synthesis tool instantly on every turn.

Your agent uses `list_voices` to inspect available profiles and `update_voice` to modify their metadata. The OpenAI Agents SDK lets you coordinate these actions across specialized agents, handing off tasks when a voice change is needed.

Your audio samples and generated voice scripts are sent directly to the speech synthesis API for processing. The Vinkius sandbox acts as a zero-trust intermediary, ensuring your raw audio files never persist on our servers after the session ends.

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