Integrations
KugelAudio MCP server for Claude and Cursor
The KugelAudio MCP server lets an AI assistant use your account directly: list voices and models and turn text into speech. You sign in with your KugelAudio account; there is no API key to copy.
How it works
What the integration does
Sign in, then allow
The first time the assistant uses the server, a KugelAudio sign-in opens. Pick the project and press Allow.
Four tools
whoami, list_models, list_voices and synthesize_speech, which returns a one-time WAV link valid for 15 minutes.
Billed like the API
Every call is an ordinary API request in the project you picked. Delete the assistant key to disconnect it.
Code
Connect your assistant
In Claude on the web or desktop, add https://www.kugelaudio.com/mcp under Settings, Connectors, Add custom connector. Any client with remote MCP and OAuth works the same way.
claude mcp add --transport http kugelaudio https://www.kugelaudio.com/mcp{
"mcpServers": {
"kugelaudio": { "url": "https://www.kugelaudio.com/mcp" }
}
}Copied from the documentation at docs.kugelaudio.com/guides/mcp-server. Read the full guide
Integrations
Other integrations
LiveKit Agents
Official TTS plugin for LiveKit Agents in Python and TypeScript.
View integrationPipecat
Official TTS service for Pipecat voice pipelines in Python.
View integrationVapi
Built-in custom TTS endpoint for Vapi assistants, no proxy needed.
View integrationCognigy
Custom speech vendor endpoint for Cognigy Voice Gateway.
View integration
Give your agent a KugelAudio voice
Create an account, copy an API key from the dashboard and pick a voice. Every integration on this page runs on the same API.