What operating systems are supported?
Windows 10 and Windows 11 are required. Other operating systems are not supported.
@leszini
Basic information
Spoken-mcp is a voice interface for the Claude Desktop app. It consists of two components: an MCP TTS server that lets Claude speak responses aloud via ElevenLabs, and an STT companion app that transcribes your speech and pastes it into Claude's input field. Supports three input
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"spoken-mcp": {
"command": "python",
"args": [
"C:\\full\\path\\to\\spoken-mcp\\tts_server.py"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
spoken-mcp turns Claude Desktop into a fully voice-enabled assistant. You speak to Claude and hear responses spoken aloud in any language supported by ElevenLabs. It consists of an MCP TTS Server (for reading responses aloud via ElevenLabs Text-to-Speech) and an STT Companion (a background app that listens, transcribes via ElevenLabs Scribe v1, and pastes into Claude's input field).
Install spoken-mcp on Windows 10/11 with Python 3.11+ and obtain an ElevenLabs API key. Run the MCP TTS server and STT companion, then choose one of three input modes: push-to-talk, VAD toggle, or always-on voice detection. A system tray icon shows the current state (idle/listening/recording). Full setup instructions are at the project’s GitHub repository.
Windows 10 and Windows 11 are required. Other operating systems are not supported.
Python 3.11 or newer, an ElevenLabs API key, and the Claude Desktop application.
The STT companion listens to your microphone and transcribes speech using ElevenLabs Scribe v1, then pastes the text into Claude’s input field. The MCP TTS server uses the speak tool to read Claude’s responses aloud via ElevenLabs Text-to-Speech.
No, spoken-mcp operates without requiring administrator rights.
Yes, spoken-mcp works with any language supported by ElevenLabs for both transcription and speech synthesis.
FACTANKER serves 1.18B+ evidence-backed facts about US companies, banks, nonprofits and federal spending, sourced from SEC EDGAR, FFIEC call reports, IRS 990 filings and USAspending. Every value carries its evidence: fil
Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi

Extract, search and tag any document — invoices, receipts, contracts, forms, or your own templates. 13 tools, one sign-in (OAuth 2.1) or API key, free FileTag tier, data residency in the EU, US, Israel or Asia.
Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN
AON MCP connects AI agents to real, buyable products and services with live pricing and tracked links—enabling builders to earn developer revenue share from attributed clicks and conversions.
Comments