// Transcribe speech from the microphone. Use when the user asks you to listen, hear, or transcribe what they say. Returns the spoken text on stdout.
Transcribe speech from the microphone. Use when the user asks you to listen, hear, or transcribe what they say. Returns the spoken text on stdout.
Speak a short summary aloud using Kokoro TTS. Use proactively at the end of any completed task to announce what was done in one sentence. Also use when the user explicitly asks to hear something spoken.
Speak a short summary aloud using Kokoro TTS. Use proactively at the end of any completed task to announce what was done in one sentence. Also use when the user explicitly asks to hear something spoken.
| name | listen |
| description | Transcribe speech from the microphone. Use when the user asks you to listen, hear, or transcribe what they say. Returns the spoken text on stdout. |
Transcribe speech from the microphone using the listen command (GPU-accelerated Moonshine ASR).
In this environment, listen is approved to run outside the sandbox via the
persisted command prefix ["listen"]; call it directly so it can access microphone
and GPU devices.
This command requires microphone access and cannot run inside the sandbox.
Ask the user to run it from the CLI prompt with !:
! listen
The user speaks, sees their words in yellow on the terminal, then presses ENTER to emit the final text to stdout and exit. ESC clears the buffer, ESC on empty quits without output.
! listen — do NOT call it via Bash (sandbox blocks mic access)