LMNT (Ultra-low Latency Speech Synthesis) Connector for AI agents.
7 live capabilities
Generate lifelike voiceovers and instant audio clones for real-time apps.
Waiting for input…
Why people use LMNT (Ultra-low Latency Speech Synthesis)
LMNT Speech Synthesis for Real-Time Conversational AI
LMNT solves this by delivering audio in milliseconds. With this Connector, your agent handles the speech synthesis instantly, making the interaction feel natural and fluid.
What Vinkius changes
You get instant, high-quality audio output without leaving your AI interface.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Real-time customer service bots
A developer builds a bot that speaks back immediately using generate_speech to reduce dead air during customer calls.
- Real-world use case 02
Automated narration for YouTube
A creator clones their own voice using create_voice so they can automate high-volume narrations while they sleep.
- Real-world use case 03
Multi-region content localization
A team quickly swaps voices for different regions using list_voices and get_voice to ensure the right tone for every country.
Complete set · 7capabilities
The complete LMNT (Ultra-low Latency Speech Synthesis) capability set.
These are the exact actions your AI can choose when you ask it to work with LMNT (Ultra-low Latency Speech Synthesis).
01—04
4 capabilities in this set.
Part of 7 available through LMNT (Ultra-low Latency Speech Synthesis).
- 01 Capability
Create voice
Make a new voice clone instantly by uploading audio samples. This is the fastest way to add new voices to your library.
- 02 Capability
Generate speech
Turn text into a base64 encoded audio stream for immediate playback. This capability is optimized for ultra-low latency.
- 03 Capability
Get account
Check your current subscription plan and see how many characters you have left. It helps you avoid hitting your limits unexpectedly.
- 04 Capability
Get voice
Pull specific details and information about a single voice. Use this to verify settings for a particular clone.
05—07
3 capabilities in this set.
Part of 7 available through LMNT (Ultra-low Latency Speech Synthesis).
- 05 Capability
List voices
See a full list of all the voices available to your account. This gives you a quick overview of your library.
- 06 Capability
Update voice
Change the settings or properties of an existing voice clone. Use this to refine your custom voices on the fly.
- 07 Capability
Delete voice
Remove a specific voice from your library using its unique ID. This helps keep your voice list organized.
Set up in minutes
One URL. Then ask LMNT (Ultra-low Latency Speech Synthesis) to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use LMNT (Ultra-low Latency Speech Synthesis) from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_HUL7nYTyeZDkCPGI9P4KyMLRDb0Pv4CZVWjuWJeF/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it LMNT (Ultra-low Latency Speech Synthesis), and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable LMNT (Ultra-low Latency Speech Synthesis) for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_HUL7nYTyeZDkCPGI9P4KyMLRDb0Pv4CZVWjuWJeF/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the LMNT (Ultra-low Latency Speech Synthesis) URL.
- Step 03
Save and start
Save the connection and enable LMNT (Ultra-low Latency Speech Synthesis) in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"lmnt-ultra-low-latency-speech-synthesis": {
"url": "https://edge.vinkius.com/vk_preview_HUL7nYTyeZDkCPGI9P4KyMLRDb0Pv4CZVWjuWJeF/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using LMNT (Ultra-low Latency Speech Synthesis)
Open Agent mode in chat and ask: "Using LMNT (Ultra-low Latency Speech Synthesis), help me...". 7 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"lmnt-ultra-low-latency-speech-synthesis": {
"url": "https://edge.vinkius.com/vk_preview_HUL7nYTyeZDkCPGI9P4KyMLRDb0Pv4CZVWjuWJeF/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using LMNT (Ultra-low Latency Speech Synthesis)
Ask Copilot: "Using LMNT (Ultra-low Latency Speech Synthesis), help me...". 7 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"lmnt-ultra-low-latency-speech-synthesis": {
"url": "https://edge.vinkius.com/vk_preview_HUL7nYTyeZDkCPGI9P4KyMLRDb0Pv4CZVWjuWJeF/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using LMNT (Ultra-low Latency Speech Synthesis)
Open Cascade and ask: "Using LMNT (Ultra-low Latency Speech Synthesis), help me...". 7 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"lmnt-ultra-low-latency-speech-synthesis": {
"url": "https://edge.vinkius.com/vk_preview_HUL7nYTyeZDkCPGI9P4KyMLRDb0Pv4CZVWjuWJeF/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using LMNT (Ultra-low Latency Speech Synthesis)
Ask Cline: "Using LMNT (Ultra-low Latency Speech Synthesis), help me...". 7 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add lmnt-ultra-low-latency-speech-synthesis --transport http "https://edge.vinkius.com/vk_preview_HUL7nYTyeZDkCPGI9P4KyMLRDb0Pv4CZVWjuWJeF/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using LMNT (Ultra-low Latency Speech Synthesis)
Ask Claude: "Using LMNT (Ultra-low Latency Speech Synthesis), show me...". 7 tools are ready
Where the request belongs
Work LMNT can move forward.
This is for developers and creators who need high-speed audio. It solves the problem of robotic, slow speech in real-time apps or the tedious manual work of managing hundreds of voice clones.
Conversational AI Developer
You use this to build voice-enabled bots that respond in real-time without noticeable lag.
Content Creator
You use this to automate high-volume narrations and clone your own voice for consistent branding.
Accessibility Engineer
You use this to build responsive capabilities that read content aloud for users with visual impairments.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsPlay.ht (Voice Cloning)
Generate ultra-realistic speech and clone voices instantly using Play.ht's advanced AI voice engines directly from your agent.
ElevenLabs
Generate lifelike speech, clone voices, and create sound effects using ElevenLabs' industry-leading AI audio technology.
Cartesia (Voice AI)
Generate lifelike AI voices, clone speech, and transcribe audio with Cartesia's state-of-the-art Sonic models directly from your AI agent.
Inworld AI
Power your AI agents with Inworld's lifelike voices, voice cloning, and advanced character orchestration routers.
Resemble AI
Generate high-quality AI voices, manage projects, and transform speech with Resemble AI's powerful voice cloning and synthesis capabilities.
Play.ht (AI Voice Generation & TTS)
Generate ultra-realistic AI voices and convert text to speech instantly using Play.ht's advanced neural engine.
Bring your own AI
Change the model, client or framework. Keep LMNT connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about LMNT.
The practical details behind the request, access and result.
How fast is the speech synthesis with the LMNT MCP?
It is designed for ultra-low latency. This means your AI agent can generate speech in milliseconds, making it fast enough for real-time conversations.
Can I use this to clone my own voice for my AI agent?
Yes, you can. You just need to provide audio samples, and the Connector will create a custom voice clone that your agent can use for any text input.
How do I manage my voice library without using a dashboard?
You can manage everything through your AI client. Just ask your agent to list, update, or delete voices from your library in plain English.
Does this work for multiple languages?
Yes, the synthesis supports multiple languages, allowing you to localize your content or build multi-lingual voice apps easily.
How can I keep track of my monthly usage limits?
You can ask your agent to check your account status at any time. It will pull your current plan info and tell you exactly how many characters you have left.
Is this suitable for real-time customer service bots?
It's perfect for that. Because it focuses on low latency, it's one of the best ways to give a customer service bot a natural, human-like speaking voice.
Can I choose different audio formats like MP3 or WAV?
Yes. The generate_speech capability 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 capability 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 capability. It returns your current usage metrics and plan details directly from the LMNT API.
One connection away
Give your agent a direct line to LMNT.
Connect LMNT once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available