Provides cloud-based text-to-speech capabilities using ElevenLabs voices to generate and broadcast audio announcements through the CastleCall system.
Enables the triggering of audio announcements on a Raspberry Pi-based home PA system via the CastleCall interface.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
An MCP server that exposes a text-to-speech announce tool for CastleCall — a home PA/announcement system for Raspberry Pi.
Supports Piper (local) and ElevenLabs (cloud) TTS providers via stdio transport.
npm install
npm run buildRelated MCP server: Rime MCP
Variable | Required | Description |
| Yes | URL of your CastleCall instance (e.g. |
| No | TTS provider: |
| When using ElevenLabs | ElevenLabs voice ID |
Add to your MCP settings:
{
"mcpServers": {
"castlecall": {
"command": "node",
"args": ["/path/to/castlecall-mcp/dist/cli.js"],
"env": {
"CASTLECALL_URL": "http://192.168.1.50:3000",
"CASTLECALL_PROVIDER": "piper"
}
}
}
}ElevenLabs example:
{
"mcpServers": {
"castlecall": {
"command": "node",
"args": ["/path/to/castlecall-mcp/dist/cli.js"],
"env": {
"CASTLECALL_URL": "http://192.168.1.50:3000",
"CASTLECALL_PROVIDER": "elevenlabs",
"CASTLECALL_VOICE_ID": "your-voice-id"
}
}
}
}announcePlay a text-to-speech announcement on CastleCall.
Parameter | Type | Required | Description |
| string | Yes | The text to announce |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Remote text-to-speech MCP server with text_to_speech and list_voices tools. Free plan.
Hosted text-to-speech MCP server: 66 voices in 9 languages, long-form narration, podcasts.
AI voice generation: text-to-speech and voice cloning from any MCP client.
MCP server exposing the AceDataCloud Fish Audio API (text-to-speech with voice conditioning)
