← Back to Skills Marketplace
330
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install pi-speaker
Description
Play TTS or audio on the Raspberry Pi (or gateway host) default speaker. Use when the user asks for an announcement, alarm, news summary, or "say X on the Pi...
Usage Guidance
This skill appears to do only what it says: generate or receive a path to an audio file and play it on the gateway host using paplay or pw-play (or the included helper script). Before enabling, verify that the gateway host actually has PulseAudio/PipeWire and the desired default sink set (Bluetooth speaker connected). Remember the agent will execute a host command (exec/bash) to play files — only enable this skill on hosts you trust. There are no required credentials and no external downloads, so there is low risk of hidden network exfiltration, but avoid running it on sensitive multi-user machines if you do not want arbitrary audible playback.
Capability Analysis
Type: OpenClaw Skill
Name: pi-speaker
Version: 1.0.1
The skill enables local audio playback by instructing the AI agent to generate TTS and then execute shell commands (pw-play, paplay, or a provided script) directly on the host system. While this functionality is aligned with the stated purpose of a Raspberry Pi speaker, the instructions explicitly direct the agent to use the bash/exec tool without sandboxing or with elevated privileges. This represents a high-risk capability and a significant attack surface, as it relies on the agent to correctly handle shell execution and file paths (SKILL.md, openclaw-speaker-play.sh).
Capability Assessment
Purpose & Capability
Name/description ask to play local audio on the gateway host; the skill only requires paplay or pw-play and includes a small playback helper script that runs those binaries. These requirements match the stated purpose.
Instruction Scope
SKILL.md straightforwardly instructs the agent to generate TTS (using the platform's tts tool) then invoke exec/bash to call paplay/pw-play (or the included script) on the host path. It does not ask the agent to read unrelated files, access secrets, or contact external endpoints.
Install Mechanism
No install spec; script is included but nothing is auto-downloaded or executed during install. No network fetches or archive extraction are defined.
Credentials
No environment variables or credentials are requested. The binaries required (paplay/pw-play) are appropriate and proportional to playing audio.
Persistence & Privilege
Skill is not set to always: true and does not request persistent system changes or modify other skills. It simply instructs running a playback command on demand.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pi-speaker - After installation, invoke the skill by name or use
/pi-speaker - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
added homepage
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is Pi Speaker?
Play TTS or audio on the Raspberry Pi (or gateway host) default speaker. Use when the user asks for an announcement, alarm, news summary, or "say X on the Pi... It is an AI Agent Skill for Claude Code / OpenClaw, with 330 downloads so far.
How do I install Pi Speaker?
Run "/install pi-speaker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pi Speaker free?
Yes, Pi Speaker is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Pi Speaker support?
Pi Speaker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Pi Speaker?
It is built and maintained by Panda (@nobloodontheleaves); the current version is v1.0.1.
More Skills