Menu
Transcribe speech using local STT. Use when the user wants voice input or offline audio transcription.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Capture the screen and inject a short text summary into Claude's context via an in-process VLM (llama-cpp-python). No daemon. Use to feed terminal/editor/browser state to Claude for debug, fix suggestions, or summarization with minimal token cost.
Speak text aloud using local TTS. Use when the user wants Claude's output read aloud or to toggle auto-read mode.
| name | listen |
| description | Transcribe speech using local STT. Use when the user wants voice input or offline audio transcription. |
Transcribe speech using local speech-to-text.
/listen — start/stop listening via microphone/listen recording.wav — transcribe an audio file/listen --toggle — enable/disable auto-listen modepython -m cc_stt $ARGUMENTS
See .cc-senses.example.toml [stt] section for the full schema and CC_STT_* env overrides.
Prototype — config, engine protocol, mic capture, utterance buffer, PTY injection, and live listen pipeline are implemented.