sag

Convert text to natural-sounding speech via the sag CLI with ElevenLabs TTS.

386k|81.1k|Updated Nov 24, 2025

Search Tags:#text-to-speech #elevenlabs #tts #audio content #voice generation

Ready to run

npx skills add https://github.com/steipete/clawdis --skill sag

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/steipete/clawdis/tree/main/skills/sag
Command: npx skills add https://github.com/steipete/clawdis --skill sag

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sag, ELEVENLABS_API_KEY.

What problem does it solve?

This Skill transforms written content into natural-sounding audio, eliminating the need for manual recording and editing.

Core Features & Use Cases

Text-to-Speech: Generate high-quality voice output from any text input.
Voice Customization: Choose from multiple voices and control delivery with audio tags.
Use Case: When you need to create voiceovers for presentations or convert written reports into audio format for on-the-go listening.

Quick Start

Use sag to speak the text "Welcome to the team meeting starting in 5 minutes" using the Roger voice.

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 with natural-sounding voices?▼

Text-to-speech converts written content into audio using ElevenLabs' voice synthesis. The sag CLI accepts text input, applies your chosen voice and delivery settings, and outputs playable audio locally without manual recording or editing.

Can I customize voice delivery and pronunciation in text-to-speech output?▼

Yes. The sag CLI supports voice selection across multiple model variants, audio tag controls for delivery, and SSML handling for pronunciation adjustments. API-key authentication (ELEVENLABS_API_KEY) is required to access these voice customization features.

How do I automate voice content creation for presentations or reports?▼

Use sag in CLI workflows to synthesize speech from text on demand. Specify a voice, apply delivery controls via audio tags, and stream output locally for voiceovers, accessibility conversion, or on-the-go listening without manual recording.

What authentication and setup does text-to-speech synthesis require?▼

Text-to-speech via sag requires an ElevenLabs API key (ELEVENLABS_API_KEY environment variable or SAG_API_KEY as fallback). Model selection and version-specific SSML handling are configured through the sag CLI for proper voice synthesis.

Can I generate speech for accessibility or demo purposes?▼

Yes. The sag skill is designed for accessibility tasks and demos. It converts text to natural-sounding speech with voice selection and delivery controls, making content accessible for users who need audio alternatives and supporting quick demo voiceovers.