sag

Convert text into natural-sounding speech with ElevenLabs voices locally.

1|Updated Feb 1, 2026
One-click install
npx skills add https://github.com/sarathi-aiml/openclaw-zero-trust --skill sag-sarathi-aiml
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/sarathi-aiml/openclaw-zero-trust/tree/main/skills/sag
Command: npx skills add https://github.com/sarathi-aiml/openclaw-zero-trust --skill sag-sarathi-aiml

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables turn-by-turn text-to-speech playback using ElevenLabs voices locally, eliminating reliance on external voice generation services or network latency.

Core Features & Use Cases

  • On-device TTS with ElevenLabs voices for responsive, privacy-preserving speech.
  • Configurable voice selection, pronunciation tweaks, and simple prompts to tailor delivery.
  • Use Case: add spoken explanations to apps, accessibility features, or voice-enabled assistants.

Quick Start

Use sag to generate audio responses from text with ElevenLabs voices.

Frequently Asked Questions about sag

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

FAQPage Schema
How do I convert text to speech locally using ElevenLabs voices?

Yes, you can customize voice delivery by selecting specific ElevenLabs voices and applying pronunciation tweaks. The skill supports voice selection and SSML-like tags to tailor the spoken output for chatbots or accessibility tools.

Do I need an API key to generate ElevenLabs text-to-speech audio?

Local text-to-speech playback with ElevenLabs eliminates network latency from external voice generation services and preserves privacy. It provides responsive, on-device speech synthesis suitable for voice-enabled assistants and accessibility features.

Can I use SSML tags to adjust pronunciation for text-to-speech output?

You can integrate this skill into chatbots, accessibility tools, and voice-enabled assistants to add spoken explanations. It provides a mac-style say user experience for turn-by-turn text-to-speech playback using ElevenLabs voices.

What is the best way to add voice output to a chatbot without network latency?

The best way to avoid network latency is using a local text-to-speech workflow that generates ElevenLabs voice audio on your device. This approach provides responsive, privacy-preserving speech for your chatbot or assistant application.