voice-mode

Community

Unified voice I/O for hands-free dialogs.

Authorllblab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill unifies voice input and output in one place, enabling seamless audio interactions through say (TTS), listen (STT), and a duplex dialogue workflow.

Core Features & Use Cases

  • Atomic primitives: say, listen, and a duplex wrapper for continuous dialogue.
  • Duplex mode: hands-free conversation loop with language memory and simple stop conditions.
  • Cross-platform readiness: Linux and macOS with streaming and fallback modes, plus a bootstrap to install the commands.

Quick Start

Run the bootstrap script to install the atomic voice commands and begin using say, listen, and duplex.

Dependency Matrix

Required Modules

piperfaster-whisperpyaudionumpyarecordsoxreccurlpython3

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: voice-mode
Download link: https://github.com/llblab/skills/archive/main.zip#voice-mode

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.