voice-mode
Voice Mode (Super-Skill)
Purpose
This skill unifies voice output and voice input in one place:
say— text-to-speech (TTS)listen— speech-to-text (STT)duplex mode— agent orchestration (say→listen) built on the atomic scripts
Use say and listen independently, or let the agent combine them into continuous duplex dialogue.
This is an offline-first skill: STT runs locally via faster-whisper, and TTS uses local piper models after the initial voice download.
Atomic Commands
1) Speak
More from llblab/skills
evolve-context
Self-evolving context protocol across ABC-split root files (AGENTS.md, BACKLOG.md, CHANGELOG.md), human entrypoint README.md files tree, and /docs. Use after meaningful project changes, backlog drift, documentation refactors, or when you want a forced context reconciliation pass.
10cross-evolution
Horizontal Gene Transfer protocol for skills. Synchronizes best practices and architectural patterns across the skill library.
9while-true
Continuous execution-loop protocol — assess reality, refine the plan, execute the next task, repeat until a real stop condition is reached.
2