audio-reply
Generate audio replies using TTS. Trigger with "read it to me [public URL]" to fetch and read content aloud, or "talk to me [topic]" to generate a spoken response. Also responds to "speak", "say it", "voice reply".
Why use this skill?
Enable text-to-speech for OpenClaw with the audio-reply skill. Listen to web articles, conversational agent responses, and enjoy hands-free interaction.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/matrixy/audio-reply-skillWhat This Skill Does
The audio-reply skill enables your OpenClaw agent to speak directly to you. Powered by the high-performance MLX Audio TTS (chatterbox-turbo), this skill transforms text-based inputs and web content into natural-sounding speech. Whether you want to listen to a news article while multitasking or prefer a conversational audio response to your queries, this skill brings an auditory dimension to your agent interaction. It includes built-in safety guardrails to ensure that external content is fetched and processed securely without risking your local system integrity.
Installation
To add this capability to your agent, run the following command in your terminal:
clawhub install openclaw/skills/skills/matrixy/audio-reply-skill
This installs the necessary dependencies and the speech engine model, ensuring the skill is ready for immediate execution.
Use Cases
- Hands-Free Reading: Use the 'read it to me' command to listen to long-form articles, documentation, or blog posts without needing to look at your screen. This is ideal for commutes, chores, or visual breaks.
- Voice-First Interaction: Use 'talk to me' for quick updates or information retrieval where listening is more convenient than reading.
- Accessibility: Enhance your workflow by having complex technical responses read aloud, aiding in comprehension for auditory learners.
Example Prompts
- "read it to me https://example.com/latest-tech-trends"
- "talk to me about the current status of my project queue"
- "speak, please explain the concept of neural networks like I am five"
Tips & Limitations
- Safety First: The skill enforces strict URL validation. It will block attempts to reach private networks, internal IPs (like 127.0.0.1), or links containing sensitive credentials. If a site is behind a login, copy the text and ask the agent to 'speak' the pasted excerpt instead.
- Content Length: For best quality, keep conversational responses under 200 words. When using 'read it to me', the agent will summarize content over 500 words to ensure the audio remains punchy and relevant.
- Cleanup: The skill automatically cleans up temporary files after playback, ensuring your machine does not become cluttered with audio fragments. Avoid using this skill to process sensitive financial or personal records, as the intermediate text/audio might persist in local logs.
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-matrixy-audio-reply-skill": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write
Related Skills
agent-browser
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
linear
Manage Linear projects, issues, and tasks via the bundled Node CLI and the official Linear API. Use when you need to read, create, update, or organize Linear issues, projects, teams, milestones, comments, cycles, labels, and documents.
agent-registry
MANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill instead of loading agents directly from ~/.claude/agents/ or .claude/agents/. Provides lazy loading via search and get tools. Use when: (1) user task may benefit from specialized agent expertise, (2) user asks about available agents, (3) starting complex workflows that historically used agents. This skill reduces context window usage by ~95% compared to loading all agents upfront.