A local audio playback workflow that enables AI agents to play speech and sound files directly through a Raspberry Pi or gateway host speaker.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pi-speaker
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install pi-speaker using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is pi-speaker?
The pi-speaker capability is designed for scenarios where an AI agent needs to interact with its physical environment via audio. By utilizing Openclaw Skills, the gateway host can output text-to-speech (TTS) or audio files directly to the default system sink, such as a Bluetooth speaker or a local line-out. This is particularly useful for Raspberry Pi users who want their agent to provide audible feedback, voice notifications, or status updates without relying on the browser's audio output.
This workflow integrates seamlessly with existing system-level audio drivers like PipeWire or PulseAudio. It ensures that whenever a user asks for an announcement or an alarm, the Openclaw Skills framework can process the request locally on the host machine, providing a robust solution for ambient computing and smart home automation.
pi-speaker Use Cases
- Triggering audible morning news summaries or weather updates through a Raspberry Pi.
- Setting up voice-based alarms or reminders that play on a local Bluetooth speaker.
- Providing hands-free status announcements when smart home tasks are completed via Openclaw Skills.
- Playing specific audio files or sound effects as part of a localized automation sequence.
How pi-speaker Works
- The AI agent processes a user request for local audio and invokes the tts tool to convert text into a temporary audio file.
- The system captures the resulting file path on the host, ensuring the file is accessible to the local execution environment.
- The agent utilizes Openclaw Skills to call the exec tool, running playback commands like pw-play or paplay directed at the generated file.
- The agent monitors the execution process and only confirms successful playback to the user once the system returns a success exit code.
pi-speaker Setup
To use this functionality within Openclaw Skills, ensure your gateway host has the necessary audio utilities installed and a default audio sink configured. Use the following commands to prepare your environment:
# Install audio playback utilities
sudo apt-get update
sudo apt-get install pipewire-bin pulseaudio-utils
# Verify your default audio sink (e.g., Bluetooth speaker)
pactl info | grep "Default Sink"
Note: There is no standalone CLI command for this skill; it is executed by chaining the tts and exec tools.
pi-speaker Data Schema & Taxonomy
| Component | Description | Example Value |
|---|---|---|
| Source Audio | The path to the file generated by the tts tool on the host. | /tmp/openclaw/tts-voice.mp3 |
| Playback Tool | The binary used to output sound to the system sink. | pw-play, paplay |
| Prefix Handling | Logic used to strip MEDIA: prefixes from tool outputs. | /path/to/file |
| Execution Result | The status returned by the host system after playback attempt. | Exit 0 (Success) |
pi-speaker Advanced Features
- Support for custom playback scripts (e.g., openclaw-speaker-play.sh) to handle complex audio routing or volume normalization.
- Multi-stage tool orchestration within Openclaw Skills to ensure audio is generated and played sequentially without user intervention.
- Compatibility with both PulseAudio and PipeWire backends for broad hardware support.
- Intelligent error handling that detects disconnected speakers or missing audio sessions before reporting success to the user.
SKILL.md
Loading
Related Openclaw Skills
Tabstack Extractor
A robust tool for converting websites into structured JSON or clean Markdown using the Tabstack API and Babashka.
SearXNG Web Search
A privacy-preserving web search skill for AI agents that leverages self-hosted SearXNG instances to retrieve real-time data and documentation.
Tsundere Persona
An AI skill that transforms standard model responses into classic tsundere anime character dialogue.
Anime Meme Collector
An automated system for harvesting and organizing Chinese ACG memes and trending Bilibili content to improve AI cultural intelligence.
Apollo Issue Review
A professional issue triage workflow that automates reproduction, evidence-checking, and drafting maintainer-grade GitHub responses for the Apollo ecosystem.
Carrier Relationship Management
A codified expertise framework for managing carrier portfolios, negotiating freight rates, and automating logistics performance tracking.
METADATA
Featured*
