Agent Vibes OpenClaw Skill
Stream free, professional text-to-speech from voiceless servers to Linux, macOS, or Android devices with 50+ voices in 30+ languages. Two architecture options for flexible deployment - server-side TTS with audio streaming (PulseAudio) OR efficient text streaming with receiver-side TTS generation (recommended). Perfect for SSH sessions, remote AI agents, and multi-device TTS.
Why use this skill?
Add professional text-to-speech to OpenClaw with Agent Vibes. Support for 50+ voices, 30+ languages, and flexible local or server-side streaming.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/paulpreibisch/agentvibes-openclaw-skillWhat This Skill Does
The Agent Vibes OpenClaw Skill brings professional, high-quality text-to-speech (TTS) capabilities to your Linux, macOS, or Android environment. By leveraging a flexible dual-architecture approach, it supports both server-side audio streaming via PulseAudio for remote sessions and efficient receiver-side generation for low-latency local interactions. It is a comprehensive voice management system that allows users to switch between TTS providers like Piper and native macOS system voices, managing a library of over 50 voices across more than 30 languages. Whether you are working in an SSH terminal, managing an AI agent interface, or coordinating multi-device voice outputs, this skill ensures your environment remains expressive and responsive.
Installation
To integrate this voice engine into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/paulpreibisch/agentvibes-openclaw-skill
Once installed, you can begin managing your audio environment immediately using the /agent-vibes command suite. Configurations are stored locally, ensuring that your preferred voice, pretext settings, and mute status persist across reboots and new shell sessions.
Use Cases
- Remote AI Agents: Enable voice feedback for agents running on headless Linux servers by streaming audio to your local machine.
- Accessibility: Provide auditory feedback for terminal-heavy workflows, making system notifications and AI responses easier to process while away from the screen.
- Multi-Device Sync: Maintain a consistent voice profile across different hardware, allowing for seamless transitions between developer environments.
- Speech Synthesis Testing: Quickly preview and compare various voices to select the perfect persona for your specific application or user experience design.
Example Prompts
- "Agent, use /agent-vibes:switch en_US-amy-medium and set the pretext to 'System Alert' to help me identify important notifications."
- "I need to check the available options, can you run /agent-vibes:list first 5 and then preview the first two voices for me?"
- "Switch my TTS provider to piper and confirm the current voice settings, then replay the last message to ensure the audio is clear."
Tips & Limitations
- Efficiency: Use the receiver-side TTS architecture for low-bandwidth connections or environments where latency is a concern, as it offloads the compute to your local hardware.
- Customization: Don't hesitate to use
/agent-vibes:set-pretextto add personality to your AI; it helps significantly in distinguishing AI chatter from terminal noise. - Limitations: While Piper provides excellent offline performance, native macOS voices may be limited to specific operating systems. Always verify provider compatibility using
/agent-vibes:provider listif you notice audio output failures.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-paulpreibisch-agentvibes-openclaw-skill": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read