LMNT MCP for AI. Ultra-Low Latency Speech Synthesis and Voice Cloning

Q: How do I check if my account has enough credits for high-volume speech synthesis using generatespeech?

Call the getaccount tool. This returns your current plan details, showing exactly how many characters you have consumed and what your remaining monthly limit is.

Q: What do I need to use the createvoice tool for cloning a new voice?

You must provide an audio sample file. The createvoice tool takes this input, processes it, and returns a unique voice ID that you can then use with generatespeech.

Q: I have too many old voices; how do I clean up my asset list?

First, check your full inventory using listvoices. Once you confirm an unused voice ID, you can call deletevoice to remove it from the active set.

Q: Can I modify a voice's metadata without changing its core sound?

Yes. Use the updatevoice tool. This lets you adjust parameters or labels for an existing asset ID using getvoice as your reference, without affecting the audio itself.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

How this MCP server connects to your AI agent

LMNT provides ultra-low latency speech synthesis, letting your AI client generate high-fidelity audio in milliseconds. Use it to clone voices instantly from samples or manage all your custom voice assets through dedicated tools like `create_voice` and `list_voices`.

It's built for real-time applications where speed matters.

What AI agents can do with LMNT (Ultra-low Latency Speech Synthesis) Automation

Create voice

Takes an audio sample and generates a unique ID for a new cloned voice asset.

Delete voice

Removes a specific, existing voice from the account using its unique identifier.

Generate speech

Converts input text into an audio stream and returns it encoded in base64 format for playback or download.

+ 4 more capabilities included

Synthesize Speech from Text

The agent calls generate_speech to convert written text into a base64 encoded audio stream, supporting multiple languages.

Create Voice Clones

The agent executes create_voice by uploading an audio sample and instantly generating a new, usable voice ID.

List All Available Voices

The agent runs list_voices to retrieve a full inventory of all custom and system voices associated with the account.

Retrieve Voice Details

The agent uses get_voice or get_account to pull specific metadata about an existing voice ID or check usage limits.

Update and Delete Assets

The agent manages the asset lifecycle by calling update_voice for modifications or delete_voice to remove unused voices.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

What AI agents can do with LMNT (Ultra-low Latency Speech Synthesis) MCP Server: 7 Tools

Access seven functions to generate, clone, and manage high-quality voice assets directly from your AI client.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using LMNT (Ultra-low Latency Speech Synthesis) on Vinkius

Create Voice

Takes an audio sample and generates a unique ID for a new cloned voice asset.

Delete Voice

Removes a specific, existing voice from the account using its unique identifier.

Generate Speech

Converts input text into an audio stream and returns it encoded in base64 format for...

Get Account

Retrieves the current account usage metrics, including character counts used and...

Get Voice

Fetches detailed metadata for a single voice ID, showing its properties and status.

List Voices

Returns an array of all available voices in the account, allowing you to inspect their IDs and basic attributes.

Update Voice

Modifies metadata for an existing voice ID without changing the underlying audio samples or model.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The LMNT integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "lmnt-ultra-low-latency-speech-synthesis": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the LMNT tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"lmnt-ultra-low-latency-speech-synthesis": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with LMNT (Ultra-low Latency Speech Synthesis), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 7 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Manual Voice Generation Was Always a Pain Point, Solved with Vinkius AI Gateway

Think about how you handle audio now: you record a script, send it to an external service, wait 30 minutes for the render queue, download a massive ZIP file, and then upload that asset into your project's CMS. It’s slow, it costs money, and it requires multiple handoffs.

With LMNT, all of that disappears. You simply tell your agent to run `generate_speech` with the text and voice ID you want. The audio is generated instantly and returned directly as a base64 stream—it's ready for use right in your application layer.

LMNT (Ultra-low Latency Speech Synthesis) MCP Server

Before, creating a new voice clone meant spending hours recording clean samples and waiting days for the service to approve it. You were stuck using generic system voices because your custom assets weren't ready.

Now you run `create_voice` with just an audio sample, and within minutes, you have a unique ID and a fully usable voice asset. This speed changes how fast you can iterate on product features.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

text-to-speech

voice-cloning

ai-audio

low-latency

speech-synthesis

What your AI can actually do with this

You're building something real-time—a conversational agent, maybe live content localization—and latency is everything. This server gives you ultra-low latency speech synthesis and voice cloning, generating high-fidelity audio in milliseconds for your AI client. You gotta manage these assets fast.

To turn text into sound, the generate_speech tool takes written input, lets you select a language, and converts it straight into an audio stream encoded in base64 format; that's ready to play or download right away.

When you need a new voice model, cloning is quick. You run create_voice, upload your sample audio, and the server instantly generates a unique ID for that brand-new cloned voice asset. This capability lets you replicate voices on the fly without spending time recording long sessions.

Managing your entire library of voices is straightforward. You use list_voices to pull up a full inventory, giving you IDs and basic attributes for every custom and system voice in the account. If you only care about one specific asset, you can fetch detailed metadata using get_voice. For an overview of all assets, you've got that list.

You control the lifecycle of those assets too. You modify existing voices by calling update_voice to change its associated metadata without touching the underlying audio samples or model itself. When a voice is useless clutter, you delete it using delete_voice, pointing directly at the specific ID you want gone.

Beyond asset management, you track your usage with get_account; this tool retrieves critical metrics like how many characters you've used up and what your remaining plan limits are. It keeps you in the loop on billing right out of the gate. This architecture means your agent can handle synthesis, cloning, listing, checking details, modifying assets, deleting junk, and monitoring usage—all through direct function calls.

Built · Hosted · Managed by Vinkius LMNT Speech Synthesis - Low Latency Voice Cloning MCP Server

Server ID 019e5d2e-d14c-7040-974b-5b2c95f9c83f

Vinkius Inspector

Compliance Grade A

Score 90/100

Report View Report ↗

Here's how it actually works

The bottom line is, your AI client treats audio generation and voice management like any other function call—it's just another tool in the conversation.

Subscribe to the LMNT MCP Server and provide your API Key to your AI client.

Instruct your agent to perform a specific action (e.g., 'Generate speech for X text using voice Y').

The agent calls the appropriate tool (generate_speech, create_voice, etc.) and receives the resulting audio data or asset metadata.

Who is this actually for?

Developers building real-time conversational interfaces. Content creators needing to localize massive volumes of audio quickly. Accessibility teams requiring responsive, high-quality text-to-speech tools. You're here because your current voice pipeline is either too slow or requires manual uploads.

Conversational AI Developer

Integrating live speech synthesis into a chatbot framework, needing the speed and reliability of generate_speech for real-time responses.

Localization Specialist

Managing hundreds of voiceovers across different markets, using tools like list_voices and create_voice to maintain a consistent library.

Content Marketing Manager

Automating the creation of video voice tracks or podcast intros, relying on the API to generate audio streams without human intervention.

What Changes When You Connect

Speed is the key benefit. By using generate_speech, your agent delivers audio in milliseconds, making it suitable for live conversational AI where latency kills the experience.

You maintain full control over your voice library. Tools like list_voices and get_voice let you audit every asset before running a job, so you never use the wrong ID again.

Voice cloning is instant. Running create_voice means you upload samples and immediately get a functional, reusable voice ID for generating speech, bypassing weeks of recording studio time.

Usage tracking is built in. Before massive campaigns, check your limits with get_account. This prevents billing surprises when running high-volume jobs.

Asset management is clean. You can delete old or unused assets using delete_voice, keeping your voice inventory streamlined and reducing clutter.

See it in action

01 01

Building a Real-Time Chatbot

A developer needs their chatbot to respond audibly, mimicking a human voice. Instead of relying on slow cloud APIs, they configure the agent to use generate_speech with an ultra-low latency connection. The result is immediate audio output that feels conversational and natural.

02 02

Localizing a Corporate Training Module

A content creator has a video script in English but needs it localized to Mandarin for a global audience. They use create_voice with samples of native speakers, then call generate_speech repeatedly, specifying the target language and voice ID for every segment.

03 03

Auditing Voice Assets

An operations team needs to know which voices are active but haven't been used in months. They run list_voices, inspect the full list, and then use get_voice on suspicious IDs before deciding if they need to clean up by running delete_voice.

04 04

Scaling Up Production Capacity

A startup is preparing for a major marketing push. They first call get_account to verify their remaining monthly character limit, then use the confirmed capacity to run high-volume speech synthesis jobs using generate_speech, ensuring they don't exceed their plan.

The honest tradeoffs

Assuming voice quality from a list.

Anti-pattern

The agent just calls list_voices and blindly picks the first available ID, hoping it sounds right for the new script. This results in inconsistent tone or an unsuitable accent.

The Fix

First, use get_voice on several potential IDs to check their specific metadata (e.g., pitch range, language support). Then, run a sample text through generate_speech before committing to the final production audio.

Ignoring account limits.

Anti-pattern

The system runs a massive batch of 10,000 word documents through synthesis jobs without checking usage. The process fails on the last few calls due to exceeding the monthly quota.

The Fix

Always check get_account first. This gives you visibility into your current character consumption and when the billing cycle resets, preventing unexpected run failures.

Overwriting a voice accidentally.

Anti-pattern

A developer calls update_voice with new metadata but doesn't verify which specific version they are modifying. They lose critical historical data or change essential parameters.

The Fix

Use the specific ID retrieved from get_voice to ensure you are targeting the exact asset. Always confirm the voice's properties in a separate read call before running any update.

When It Fits, When It Doesn't

Use this MCP Server if your primary requirement is converting text into speech or cloning voices, and low latency is non-negotiable. If you are building anything conversational—a chatbot, an IVR system, or a live guided tour—this toolset is necessary because of generate_speech's speed.

Don't use this if your only need is simple audio file storage (use cloud object storage instead) or if you just need to transcribe existing audio (you need a different transcription service). If you only want basic text formatting and don't care about the synthesized voice, this server is overkill. You must be ready to call one of the seven listed tools for any functionality.

Questions you might have

How do I check if my account has enough credits for high-volume speech synthesis using generate_speech? +

Call the get_account tool. This returns your current plan details, showing exactly how many characters you have consumed and what your remaining monthly limit is.

What do I need to use the create_voice tool for cloning a new voice? +

You must provide an audio sample file. The create_voice tool takes this input, processes it, and returns a unique voice ID that you can then use with generate_speech.

I have too many old voices; how do I clean up my asset list? +

First, check your full inventory using list_voices. Once you confirm an unused voice ID, you can call delete_voice to remove it from the active set.

Can I modify a voice's metadata without changing its core sound? +

Yes. Use the update_voice tool. This lets you adjust parameters or labels for an existing asset ID using get_voice as your reference, without affecting the audio itself.

What should I do if a call to `generate_speech` fails? +

The API returns specific error codes and structured messages. Check the documentation for common failure reasons, such as unsupported text characters or invalid voice IDs, and refine your input parameters.

How do I handle the audio data returned by `generate_speech`? +

The tool sends a base64 encoded stream. Your AI client must decode this string back into raw binary data before you can play or save the resulting audio file (e.g., MP3).

Are there rate limits when I use the `list_voices` tool? +

Yes, standard API rate limits apply to all endpoints. If your agent sends too many requests quickly, you will receive a 429 error; implementing an exponential backoff strategy is required.

What details does the `get_voice` tool provide for a specific ID? +

It returns detailed metadata about that voice. This includes its unique ID, supported languages, and usage parameters, letting you confirm compatibility before making a large generation call.

Can I choose different audio formats like MP3 or WAV? +

Yes. The generate_speech tool allows you to specify formats like mp3, wav, or mulaw, along with custom sample rates to fit your application's needs.

How do I create a new voice clone? +

Use the create_voice tool by providing a name and a base64-encoded audio sample. The system will process the file and return a new Voice ID for immediate use.

How can I check how many characters I have left in my plan? +

Run the get_account tool. It returns your current usage metrics and plan details directly from the LMNT API.

How this MCP server connects to your AI agent

What AI agents can do with LMNT (Ultra-low Latency Speech Synthesis) Automation

Create voice

Delete voice

Generate speech

What AI agents can do with LMNT (Ultra-low Latency Speech Synthesis) MCP Server: 7 Tools

Create Voice

Takes an audio sample and generates a unique ID for a new cloned voice asset.

Delete Voice

Removes a specific, existing voice from the account using its unique identifier.

Generate Speech

Converts input text into an audio stream and returns it encoded in base64 format for...

Get Account

Retrieves the current account usage metrics, including character counts used and...

Get Voice

Fetches detailed metadata for a single voice ID, showing its properties and status.

List Voices

Returns an array of all available voices in the account, allowing you to inspect their IDs and basic attributes.

Update Voice

Modifies metadata for an existing voice ID without changing the underlying audio samples or model.

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Built on the Model Context Protocol (MCP) for Claude, ChatGPT, Cursor, and more

Manual Voice Generation Was Always a Pain Point, Solved with Vinkius AI Gateway

LMNT (Ultra-low Latency Speech Synthesis) MCP Server

text-to-speech

voice-cloning

ai-audio

low-latency

speech-synthesis

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

Building a Real-Time Chatbot

Localizing a Corporate Training Module

Auditing Voice Assets

Scaling Up Production Capacity

The honest tradeoffs

Assuming voice quality from a list.

Ignoring account limits.

Overwriting a voice accidentally.

When It Fits, When It Doesn't

Questions you might have