Gives any text-based AI a voice and ears inside a Discord voice channel by transcribing speech, relaying to an LLM/agent, and speaking replies back.
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_CONFIG— Configure everything through one JSON file (path from $ or the first CLI argument).VOICE_NO_DISCORDVOICE_NO_MAINVOICE_VAD_SOCKWHISPER_MODEL— stt.env object {} Extra environment variables for the STT process (e.g. , WHISPER_COMPUTE). optionalWHISPER_DEVICE— src/stt.py (faster-whisper): WHISPER_MODEL (default small.en),WHISPER_COMPUTE— stt.env object {} Extra environment variables for the STT process (e.g. WHISPER_MODEL, ). optionalWHISPER_INITIAL_PROMPTVOICE_STT_FIXUPSVOICE_STT_SOCKPIPER_VOICE— tts.env object {} Extra environment variables for the TTS process (e.g. , PIPER_VOICE_DIR). optionalPIPER_VOICE_DIR— tts.env object {} Extra environment variables for the TTS process (e.g. PIPER_VOICE, ). optionalVOICE_TTS_SPEED— tts.speedFile string \ null null Path to a file containing a single float. Its contents are read fresh before each reply and passed as (pitch-preserved playback speed). optionalVOICE_TTS_SOCKVOICE_VAD_ONNX[](https://m8ven.ai/mcp/codyslater-broca-machina-1f2i4p)