Command Claude Code
Enter explore mode - think through ideas, investigate problems, clarify requirements.
29 tagged speech-to-text, measured the same way as everything else here.
Browse within: dictation 14Apple Silicon 11asr 7bun 7coreml 7openclaw 7text-to-speech 7plugin 6accessibility 5experimental 5stt 5workflow 5
Command Claude Code
Enter explore mode - think through ideas, investigate problems, clarify requirements.
Command Claude Code
Run the full pre-push verification gate (bun + rust) per CLAUDE.md's VERIFY BEFORE PUSHING rules.
Command Claude Code
Create a gitignored worktree off fresh origin/main per CLAUDE.md's "MAIN STAYS IN ROOT" rule.
Command
Add a word to your voice vocabulary.
Command
Teach idiolect what the recogniser misheard.
Command
Check the idiolect relay, settings and vocabulary.
Command
Configure voice-to-claude settings - model, hotkey, output mode.
Command
Start the voice dictation daemon.
Command
Check voice-to-claude daemon status and configuration.
Command
Start the noisy-coding voice backend (Docker) and walk through first-time setup.
Command
Update the noisy-coding voice backend (Docker) to the latest release.
Command
Watch any video and get a transcript — even without an API key. Extends /watch with a local speech-to-text fallback.
Command
Jump In and add spoken guidance.
Command
Start talking with Cadence Code.
Command
Choose Cadence Code speech models.
Command
Enable voice dictation and start the Wheel to Talk backend.
Command
Report whether Wheel to Talk is running and configured.
Command
Stop the Wheel to Talk backend.
Command
User speaks the prompt, which is sent to the Model, the received response is spoken/read aloud in a loop.