Voice input for Claude Code — speak Vietnamese or English; hold a hotkey, speak, release, and the transcribed text is cleaned and pasted into the input box for editing before sending.
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.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
process.env. You'll be asked to provide them before it can run.CLVOICE_AUTO_PASTE— ❌ true Auto-paste (Ctrl+V) into the focused window. false = clipboard only.CLVOICE_CLEAN— ❌ true Clean filler words via Groq LLM (+~0.4s, needs GROQ_API_KEY, fail-open). 0 to disable.CLVOICE_CLEAN_MODEL— ❌ llama-3.3-70b-versatile Groq chat model for cleanup.CLVOICE_DEFAULT_SECONDS— ❌ 15 Default record duration (MCP tool path).CLVOICE_FFMPEG_PATH— ❌ ffmpeg Path to the ffmpeg binary.CLVOICE_GEMINI_MODEL— ❌ gemini-2.5-flash Gemini model (switch if a model 404s).CLVOICE_GROQ_MODEL— ❌ whisper-large-v3-turbo Groq Whisper model.CLVOICE_HOTKEY— ❌ true Host the push-to-talk watcher in the server. 0 to disable.CLVOICE_LANG— ❌ auto Spoken language: auto (detect VI/EN, recommended), vi, or en.CLVOICE_MAX_SECONDS— ❌ 60 Hard cap on record duration.CLVOICE_MIC_DEVICE— env "=<MIC>" ^CLVOICE_STT— Groq STT, hotkey, and cleanup are all default-on, so they don't need env vars. To use Gemini instead: add --env =gemini --env GEMINI_API_KEY=....GEMINI_API_KEY— Groq STT, hotkey, and cleanup are all default-on, so they don't need env vars. To use Gemini instead: add --env CLVOICE_STT=gemini --env =....GROQ_API_KEY— env =<KEY> ^[](https://m8ven.ai/mcp/tvtdev94-clvoice-mcp-ncrorh)