← Back to Skills Marketplace
say
by
tobihagemann
· GitHub ↗
· v1.0.2
743
Downloads
0
Stars
2
Active Installs
3
Versions
Install in OpenClaw
/install say
Description
Text-to-Speech via macOS say command with Siri Natural Voices. Use for generating speech audio, TTS clips, or speaking text aloud on macOS.
Usage Guidance
This skill is coherent for on-device macOS TTS: it expects the built-in 'say' binary and ffmpeg for format conversion. Be aware that following the instructions will change your user defaults (com.apple.speech.voice.prefs) to switch Siri voices/languages — this modifies system voice settings for your account and may affect other apps. Because it's instruction-only, nothing is installed by the skill itself, but the agent (if allowed to invoke the skill autonomously) could run those commands on your machine. If you want to limit surprises, run the commands manually first to confirm the behavior, ensure desired Siri voices are downloaded in System Settings, and only enable the skill if you accept that it may update your macOS speech preferences.
Capability Analysis
Type: OpenClaw Skill
Name: say
Version: 1.0.2
The skill bundle is benign. It provides instructions and examples for using macOS's `say` command for text-to-speech, including converting output with `ffmpeg`. The `SKILL.md` content is purely instructional and does not contain any prompt injection attempts, data exfiltration, persistence mechanisms, or other malicious code. The use of `defaults write` is for legitimately configuring the system's text-to-speech language, which is directly relevant to the skill's stated purpose.
Capability Assessment
Purpose & Capability
Name and description (macOS TTS via say/Siri voices) match the declared requirements (require 'say' and 'ffmpeg') and the SKILL.md content. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
Runtime instructions are focused on using say, switching the system TTS language via 'defaults write', listing voices, and converting AIFF to WAV with ffmpeg. The only noteworthy action is modifying macOS user defaults (com.apple.speech.voice.prefs), which is necessary to select Siri Natural Voices but will change user preferences — this is expected but could have side effects for the user's system voice settings.
Install Mechanism
No install spec and no code files; this is instruction-only, so nothing is written to disk by the skill itself. Low install risk.
Credentials
No environment variables or credentials are requested. The skill's access needs (local binaries 'say' and 'ffmpeg') are proportional to its purpose.
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges or modify other skills. The only persistent change it suggests is writing user defaults to change the system TTS language/voice, which is within its scope.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install say - After installation, invoke the skill by name or use
/say - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Re-trigger security scan
v1.0.1
Add metadata: OS declaration (darwin), binary dependencies (say, ffmpeg), emoji
v1.0.0
Initial release: macOS TTS with Siri Natural Voices via system voice switching
Metadata
Frequently Asked Questions
What is say?
Text-to-Speech via macOS say command with Siri Natural Voices. Use for generating speech audio, TTS clips, or speaking text aloud on macOS. It is an AI Agent Skill for Claude Code / OpenClaw, with 743 downloads so far.
How do I install say?
Run "/install say" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is say free?
Yes, say is completely free (open-source). You can download, install and use it at no cost.
Which platforms does say support?
say is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin).
Who created say?
It is built and maintained by tobihagemann (@tobihagemann); the current version is v1.0.2.
More Skills