An MCP server that converts short text summaries into spoken audio and plays them locally, designed for coding agents like Claude Code to announce task results.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.VOICE_MCP_MODEL— or convert by hand, as long as points at a ready-to-useVOICE_MCP_DEVICE— auto (cuda > mps > cpu) Override if auto-detection picks wrongVOICE_MCP_STEPS— 32 ODE sampling steps; lower = faster, some quality loss. Untested below 32 so far -- see FreyaTTS's sample()VOICE_MCP_SEED— 9 Voice identity (FreyaTTS has no speaker embedding -- seed is the voice). 9 = voiceA's locked seed per confirmed_voices/best_seeds.json[](https://m8ven.ai/mcp/ummjevel-voice-announce-mcp-1jlz1b)