Menu
View or edit voice chat configuration. Shows current settings and allows changes.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
| name | config |
| description | View or edit voice chat configuration. Shows current settings and allows changes. |
| disable-model-invocation | true |
| argument-hint | [setting=value] |
View or update voice chat settings.
Show the current configuration by reading these files in order:
~/.claude-talk/config.env (user overrides)<CLAUDE_TALK_DIR>/config/defaults.env (defaults)Also read ~/.claude-talk/active-personality and show the active personality name (e.g., "Active personality: witty-jarvis"). If the file doesn't exist, show "Active personality: (none — run /claude-talk:personality to set up)".
Display a clear summary of all settings with their current effective values, noting which are defaults and which are user-set.
Show current audio server status using the Python CLI (use Bash):
source ~/.claude-talk/venvs/wlk/bin/activate && claude-talk server status
Also show audio devices (use Bash):
claude-talk devices
Show the active AUDIO_DEVICE setting and what it resolves to (if "auto" or unset, note that auto-detection is active).
Also show available TTS voices:
say -v '?' | head -20
Parse the argument as KEY=VALUE (e.g., VOICE=Karen, MIC_GAIN=4.0, AUDIO_DEVICE=2, AUDIO_DEVICE=auto).
Update ~/.claude-talk/config.env by adding or replacing the line with that key.
Confirm the change to the user.
Show help for claude-talk voice chat commands.
Start a voice conversation with Claude. Launches whisper.cpp STT and audio capture. macOS only.
Spawn or manage voice teammates. Each teammate is a separate Claude personality in its own tmux pane.
Install claude-talk and personalize your voice assistant. Sets up dependencies, then lets you choose a name, voice, and personality. macOS (Apple Silicon) only.
Set system volume to a specific level (0-100) during voice chat
Quick single voice exchange. Speaks a prompt, captures one response via TTS. No persistent session needed.