agentvibes-openclaw-skillStream 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.
Install via ClawdBot CLI:
clawdbot install agentvibes-openclaw-skillManage your text-to-speech voices across multiple providers (Piper TTS, Piper, macOS Say).
Mute all TTS output (persists across sessions)
/agent-vibes:muteUnmute TTS output
/agent-vibes:unmuteList all available voices, with optional filtering
/agent-vibes:list # Show all voices
/agent-vibes:list first 5 # Show first 5 voices
/agent-vibes:list last 3 # Show last 3 voicesPreview voices by playing audio samples
/agent-vibes:preview # Preview first 3 voices
/agent-vibes:preview 5 # Preview first 5 voices
/agent-vibes:preview last 5 # Preview last 5 voicesSwitch to a different default voice
/agent-vibes:switch en_US-amy-medium
/agent-vibes:switch en_GB-alan-medium
/agent-vibes:switch fr_FR-siwis-mediumDisplay the currently selected voice
/agent-vibes:getAdd a new custom voice from your Piper TTS account
/agent-vibes:add "My Voice" abc123xyz456See Getting Voice IDs section below.
Replay recently played TTS audio
/agent-vibes:replay # Replay last audio
/agent-vibes:replay 1 # Replay most recent
/agent-vibes:replay 2 # Replay second-to-last
/agent-vibes:replay 3 # Replay third-to-lastKeeps last 10 audio files in history.
Set a prefix word/phrase for all TTS messages
/agent-vibes:set-pretext AgentVibes # All TTS starts with "AgentVibes:"
/agent-vibes:set-pretext "Project Alpha" # Custom phrase
/agent-vibes:set-pretext "" # Clear pretextSaved locally in .agentvibes/config/agentvibes.json
Show all available TTS providers
/agent-vibes:provider listSwitch between providers
/agent-vibes:provider switch piper # Piper TTS - Free, offline, 50+ voices
/agent-vibes:provider switch macos # macOS Say - Native macOS voices (Mac only)Get details about a specific provider
/agent-vibes:provider info piper
/agent-vibes:provider info macos| Provider | Platform | Cost | Voices | Quality |
|----------|----------|------|--------|---------|
| Piper TTS | All platforms (Linux, macOS, WSL) | Free | 50+ in 30+ languages | ⭐⭐⭐⭐ |
| macOS Say | macOS only | Free (built-in) | 100+ system voices | ⭐⭐⭐⭐ |
On macOS, the native say provider is automatically detected and recommended!
To add your own custom Piper TTS voices:
/agent-vibes:add to add it:/agent-vibes:add "My Custom Voice" xyz789abc123def456English (US):
English (UK):
Romance Languages:
Germanic Languages:
Asian Languages:
/agent-vibes:switch en_US-lessac-medium # Clear male voice
/agent-vibes:switch en_US-ryan-high # High quality male
/agent-vibes:switch en_GB-alan-medium # British male/agent-vibes:preview 5 # Preview first 5 voices
/agent-vibes:preview last 3 # Preview last 3 voices/agent-vibes:add "My Voice" abc123xyz456
/agent-vibes:switch My Voice/agent-vibes:provider switch macos # Use native macOS voices
/agent-vibes:provider switch piper # Switch back to Piper/agent-vibes:mute # Silent mode
/agent-vibes:unmute # Restore voice/agent-vibes:preview before switching to a new voice/agent-vibes:replay to hear the last 10 TTS messages/agent-vibes:mute during intensive work sessionsEnjoy your TTS experience! 🎵
Generated Mar 1, 2026
Developers building AI agents on headless servers can use this skill to stream TTS audio to local devices for real-time voice feedback during debugging and interaction testing. It supports SSH sessions and flexible deployment architectures, making it ideal for remote development workflows.
Businesses can integrate this skill into customer service bots to provide TTS in over 30 languages, enhancing automated responses with natural-sounding voices. The mute/unmute and replay features allow for easy testing and management of voice outputs in live environments.
Educators and content creators can use the skill to generate voiceovers for tutorials, e-learning modules, or podcasts by switching between 50+ voices and previewing samples. The pretext setting helps brand audio content consistently across multiple projects.
This skill enables the creation of assistive tools that convert text to speech on Linux, macOS, or Android devices, offering offline capabilities with Piper TTS. Users can customize voices and replay recent messages for better comprehension in daily tasks.
Developers can embed TTS functionality into IoT devices or smart home systems to provide audio notifications and interactions. The skill's support for multiple platforms and voice management commands allows for seamless integration in multi-device environments.
Offer a free tier with basic TTS features and limited voices, then charge for premium access to advanced voices, custom voice additions, and priority support. This targets indie developers and small teams building AI agents or remote tools.
Sell enterprise licenses to large companies for integrating multilingual TTS into their customer support systems, with added features like analytics and SLA guarantees. This model leverages the skill's scalability and language support for B2B applications.
Create a marketplace where users can buy and sell custom Piper TTS voices, with the skill facilitating easy addition and switching. Revenue comes from transaction fees and hosting services, tapping into the growing demand for personalized audio content.
💬 Integration Tip
Start by testing the preview and switch commands to find the best voice for your use case, and ensure your deployment architecture matches your needs—server-side for audio streaming or receiver-side for efficient text handling.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection