skills.rest
enclawed
enclawedCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

sag

Generate ElevenLabs speech from text using a local sag interface.

2|Updated May 23, 2026
Search Tags:#text-to-speech#elevenlabs#voice synthesis#pronunciation#audio playback#voice replies
One-click install
npx skills add https://github.com/enclawed/enclawed-oss --skill sag-enclawed
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/enclawed/enclawed-oss/tree/main/skills/sag
Command: npx skills add https://github.com/enclawed/enclawed-oss --skill sag-enclawed

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns written text into natural-sounding speech through a simple local command flow, so you can create voice output without managing a complex audio pipeline.

Core Features & Use Cases

  • Text to Speech: Generate spoken audio from prompts for assistants, narration, or quick voice clips.
  • Voice and Delivery Control: Choose voices, adjust pronunciation, and use model-specific speaking styles for clearer results.
  • Chat Voice Responses: Create an audio reply when a user asks for a voice-based response, then return the generated file for playback.
  • Use Case: A support agent can turn a written answer into a polished spoken response for demos, presentations, or accessibility needs.

Quick Start

Use sag to convert the text I provide into a voice reply with the default voice and return the generated audio file.

Frequently Asked Questions about sag

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

FAQPage Schema
How do I generate ElevenLabs speech from text for voice replies?▼

To generate ElevenLabs speech from text, this Skill uses a local sag interface to convert written prompts into natural-sounding audio files, requiring a configured voice ID and API key for playback.

Can I adjust pronunciation and select voices for text-to-speech audio?▼

Yes, you can adjust pronunciation and select specific voices for text-to-speech audio, utilizing model-specific speaking styles and mac-style voice control to produce clearer, customized spoken results.

Do I need an API key and local binary to use ElevenLabs voice synthesis?▼

Yes, you need an ELEVENLABS_API_KEY or SAG_API_KEY, a configured voice ID, and a local sag binary installed locally to create and play back ElevenLabs voice synthesis audio.

What is the best way to create chat voice responses for an assistant?▼

The best way to create chat voice responses is turning written assistant answers into spoken audio, generating a polished voice reply file for demos, presentations, or accessibility needs.

Does ElevenLabs text-to-speech support low-latency audio playback for narration?▼

Yes, ElevenLabs text-to-speech supports low-latency audio playback, enabling quick generation of spoken audio from prompts for assistants, narration, or fast voice experiments.

Why does voice synthesis require a configured voice ID before generating audio?▼

Voice synthesis requires a configured voice ID because the local sag interface needs a specific voice target to accurately generate ElevenLabs speech and return the correct audio file.

Related Skills

Explore More Content & Communication Skills→
191854169191854169

sag

Convert text to natural-sounding speech via ElevenLabs TTS with local macOS playback.

Community
Intermediate
estebanrfpestebanrfp
1

sag

Generate natural-sounding speech from text and manage local playback via the sag CLI.

Community
Basic
yazelinyazelin
31

voice

Convert voice messages to text and generate spoken responses.

Community
Intermediate
tedtv1007-ctrltedtv1007-ctrl

sag

Synthesize ElevenLabs text-to-speech audio with local playback.

Community
Intermediate