sag

Convert text into ElevenLabs speech audio and play it back locally.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/Jnuso/OpenClaw --skill sag-jnuso
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/Jnuso/OpenClaw/tree/main/skills/sag
Command: npx skills add https://github.com/Jnuso/OpenClaw --skill sag-jnuso

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert text into natural-sounding speech and play it back locally using ElevenLabs voices, reducing manual audio generation steps.

Core Features & Use Cases

  • Text-to-speech conversion with ElevenLabs voices.
  • Local playback for demos, accessibility, and interactive assistants.
  • Use Case: Quickly vocalize prompts or responses in your personal AI workflows.

Quick Start

Speak a message aloud using sag, for example sag 'Hello there'.

Frequently Asked Questions about sag

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text into speech and play it back locally using ElevenLabs voices?

To convert text into speech locally, this tool processes your text input via the ElevenLabs API and plays the resulting audio playback directly on your machine, acting as a personal assistant voice generator.

What is needed to run text-to-speech conversion with a mac-style say command interface?

Running text-to-speech conversion requires an ELEVENLABS_API_KEY or SAG_API_KEY for voice generation, and the sag binary installed via Homebrew to execute local audio playback properly.

Can I use ElevenLabs text-to-speech for interactive voice demos and accessibility features?

Yes, you can use ElevenLabs text-to-speech for interactive voice demos and accessibility features, as it quickly vocalizes prompts or responses within your personal AI workflows.

How does local audio playback work when generating speech from text in my workflows?

Local audio playback works by sending your text to ElevenLabs for natural-sounding speech generation, then automatically playing the synthesized voice back on your local system without manual audio generation steps.