M
MCP Voice Summary
Reads AI coding-task summaries aloud through offline SAPI5 or neural Edge voices.
Install MCP Voice Summary
Pick your client, then add it in one click or paste the config.
~/Library/Application Support/Claude/claude_desktop_config.json{
"mcpServers": {
"mcp-voice-summary": {
"command": "uvx",
"args": [
"mcp-voice-summary"
]
}
}
}
Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.
Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.
Overview
Use cases
- Hear coding-task completion summaries
- Provide spoken feedback for accessibility
- Monitor agent changes hands-free
- Switch spoken language during a session
Key features
- Offline SAPI5 and neural Edge speech
- Asynchronous summary playback queue
- Runtime language and gender selection
- Automatic system-language voice selection
- Summary redaction and queue controls
How MCP Voice Summary works
Tools2
What MCP Voice Summary lets your agent do. Expand a tool for its parameters.
Security & health
What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.
ActiveLast checked 1d ago
Recent health check succeeded.
Supply-chain signal
No high-severity advisories surfaced by our automated scan.
Critical 0High 0Medium 0Low 0
Scanned 1d ago via OSV.dev · mcp-voice-summary (PyPI)
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks — not a rating.
Last commit11d agoMost recent push to the default branch.
Tools exposed2Callable tools this server registers over MCP.
Reviews
No reviews yet — be the first to share how it worked for you.
Frequently Asked Questions about MCP Voice Summary
mcp-voice-summary is an MCP server that connects an AI coding assistant to speech playback through Edge neural voices or offline SAPI5 voices. Its main tools, `speak_summary` and `set_language`, read task summaries aloud and let the assistant change language or gender settings during a session.
Install it with `pip install mcp-voice-summary`, then point your MCP client at the `mcp-voice-summary` command. You can also configure `uvx` with the package name to run it without a separate installation.
Yes, mcp-voice-summary works with Cursor through its standard MCP configuration. Add the server command to the client configuration, optionally set environment variables such as `VOICE_ENGINE`, and restart the client after configuration changes.
Yes, use the `sapi5` engine for offline speech. Windows uses installed SAPI5 voices, macOS requires `pyttsx3`, and Linux offline use requires espeak-ng and a compatible audio player. The `edge` engine instead requires an internet connection for each utterance.
Change it with the `set_language` tool or set `VOICE_LANGUAGE` in the MCP configuration. Runtime changes apply to later utterances, while configuration changes require restarting the MCP client. The server otherwise follows the operating system language.
Related MCP servers
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/mcp-voice-summary)HTML Embed
<a href="https://allmcps.com/mcp/mcp-voice-summary"><img src="https://allmcps.com/api/badge/mcp-voice-summary?style=directory" alt="MCP Voice Summary on AllMCPs" /></a>