Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@leanvox-mcp Read this paragraph aloud using the podcast_conversational_female voice"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Use Leanvox TTS directly from Claude, ChatGPT, Cursor, and any MCP-compatible AI assistant.
Zero code. One config line. Instant text-to-speech in your AI tools.
Add to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"leanvox": {
"command": "npx",
"args": ["-y", "leanvox-mcp"],
"env": {
"LEANVOX_API_KEY": "lv_live_your_key_here"
}
}
}
}Restart Claude Desktop. Done. ✨
Settings → MCP → Add Server:
{
"leanvox": {
"command": "npx",
"args": ["-y", "leanvox-mcp"],
"env": {
"LEANVOX_API_KEY": "lv_live_your_key_here"
}
}
}Add to .vscode/mcp.json:
{
"servers": {
"leanvox": {
"command": "npx",
"args": ["-y", "leanvox-mcp"],
"env": {
"LEANVOX_API_KEY": "lv_live_your_key_here"
}
}
}
}claude mcp add leanvox -- npx -y leanvox-mcpSet your API key:
export LEANVOX_API_KEY="lv_live_your_key_here"Related MCP server: MCP TTS Server
Once connected, just ask your AI assistant in natural language:
"Read this paragraph aloud using the podcast_conversational_female voice"
"Create a podcast dialogue between two speakers about AI"
"Clone my voice from this audio file"
"What voices are available?"
"Check my Leanvox balance"
The AI assistant handles everything — no code needed.
Tool | Description |
| Generate speech from text |
| Stream audio to a file |
| Create multi-speaker dialogue |
| Browse available voices |
| Transcribe audio or schedule async STT jobs |
| Get async TTS/STT job status |
| List async TTS/STT jobs |
| Clone a voice from audio |
| Design a voice from a description |
| Check account balance |
Resource | URI | Description |
Voices |
| All available voices |
Curated |
| 14 curated Pro voices |
History |
| Past generations |
Account |
| Balance & usage |
Prompt | Description |
| Convert text to natural speech |
| Create a multi-speaker podcast |
| Clone a voice from reference audio |
Get your API key at leanvox.com/dashboard.
Pass it via:
Environment variable LEANVOX_API_KEY (recommended)
Config file ~/.lvox/config.toml
Node.js 18+
Leanvox API key (get one free)
# Run directly
npx leanvox-mcp
# Or install globally
npm install -g leanvox-mcp
leanvox-mcp"Tool not found" — Restart your AI app after adding the config.
"Authentication error" — Check your LEANVOX_API_KEY is set correctly.
"Connection refused" — Make sure Node.js 18+ is installed: node --version
Leanvox — Main site
API Docs — Full API reference
Python SDK — pip install leanvox
Node.js SDK — npm install leanvox
GitHub — Source & issues
MIT
leanvox-mcp — Text-to-speech for the AI era.
This server cannot be deployed
AI voice generation: text-to-speech and voice cloning from any MCP client.
MCP server for Text-to-Speech
Generate game-ready 3D models, textures, and audio from natural language, over MCP.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
