Stats
Actions
Tags
How this skill is triggered — by the user, by Claude, or both
Slash command
/claudemic:listenThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Voice-to-text input using the microphone.
Voice-to-text input using the microphone.
When the user wants to speak instead of type — e.g., "listen to me", "use my mic", "dictate", "voice input", or "/listen" — use the mcp__claudemic__listen tool to capture and transcribe their speech.
mcp__claudemic__listen tool. It will record audio from the user's microphone and return transcribed text.If the listen tool returns an API key error, guide the user through setup:
mcp__claudemic__setup with their OpenAI API key.Use mcp__claudemic__status to check if the API key is configured and an audio input device is available.
npx claudepluginhub ojassurana/claudemic --plugin claudemicRecords and transcribes meetings/calls/voice memos locally (whisper.cpp/parakeet.cpp). Supports start/stop, live transcript, and status checking.
Sets up and tests text-to-speech and transcription backends (sag, OpenAI TTS, macOS say, Whisper). Run `/agent:voice` for status, setup, or test.
Guides Wispr Flow voice-to-text API integration via WebSocket streaming or REST for dictation, code-aware transcription, and voice apps. Includes auth, errors, audio specs.