Provide say, listen, and duplex voice commands for Linux and macOS.
npx skills add https://github.com/llblab/skills --skill voice-mode
Please help me install this Agent Skill. Skill: voice-mode Source: https://github.com/llblab/skills/tree/main/voice-mode Command: npx skills add https://github.com/llblab/skills --skill voice-mode
This skill unifies voice input and output in one place, enabling seamless audio interactions through say (TTS), listen (STT), and a duplex dialogue workflow.
Run the bootstrap script to install the atomic voice commands and begin using say, listen, and duplex.
High-intent search queries and answers about installing and using this skill.
To add voice I/O to an automated workflow, you can use a unified skill that provides atomic say, listen, and duplex commands. This enables hands-free dialogs with streaming and fallback modes across Linux and macOS environments.
Yes, you can run hands-free duplex conversations on Linux. The duplex mode supports continuous dialogue loops with language memory and simple stop conditions, utilizing a bootstrap script to install the required atomic voice commands.
No, you do not need to manually install Piper and faster-whisper models for TTS and STT. The skill features auto-download capabilities for voice models during the bootstrap setup process.
The best way to achieve cross-platform voice automation is using a self-contained skill that abstracts audio interactions into atomic primitives. It supports both macOS and Linux with streaming and fallback modes for robust, real-world conversations.
Voice automation requires dependencies like pyaudio and sox because they handle audio capture, processing, and playback across different platforms. The skill unifies these tools internally to provide seamless streaming and fallback audio modes.
Fallback modes for speech-to-text provide robustness when streaming fails, but may lack real-time processing capabilities. The skill uses faster-whisper for STT, ensuring functionality continues even when primary streaming audio channels encounter issues.
KAIROS7-team3Integrate OpenAI Whisper STT for voice recognition and ROS2 command processing.
wentbackwardClone voices for TTS and transcribe speech via OpenAI-compatible endpoints.
jx1100370217Configure local TTS and STT voice capabilities for OpenClaw.
TheArchitectitUnify text-to-speech, transcription, audio conversion, and editing workflows.
