sag

Convert text to speech via ElevenLabs TTS with configurable voices and pronunciation.

2.5k|423|Updated Mar 28, 2026
One-click install
npx skills add https://github.com/Bitterbot-AI/bitterbot-desktop --skill sag-bitterbot-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/sag
Command: npx skills add https://github.com/Bitterbot-AI/bitterbot-desktop --skill sag-bitterbot-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Convert text to speech using ElevenLabs TTS to provide natural, expressive audio output within local apps and workflows, removing the need for manual narration or external services for every prompt.

Core Features & Use Cases

  • Voice-enabled narration for chats, tutorials, accessibility, and demos.
  • Voice selection and pronunciation tweaks with model preferences and language options.
  • Local playback integration and simple prompts for quick audio feedback in UIs.

Quick Start

Speak a sentence using sag to generate ElevenLabs TTS audio.

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 using ElevenLabs TTS in my local app?

To convert text to speech using ElevenLabs TTS, you provide a text prompt and configure your preferred voice to generate natural audio output for local playback within your app workflows.

Do I need an API key to generate TTS audio with this voice UX?

Yes, generating TTS audio requires an ELEVENLABS_API_KEY or a SAG_API_KEY configured in your environment to authenticate requests and enable voice selection and audio playback features.

Can I customize voice selection and pronunciation for text-to-speech playback?

Yes, you can customize voice selection and apply pronunciation tweaks for text-to-speech playback, enabling configurable voices and language options tailored to specific accessibility workflows and demos.

What is the best way to add voice narration to chat interfaces and tutorials?

The best way to add voice narration to chat interfaces is using a mac-style voice UX integrated with ElevenLabs TTS, which enables quick audio generation through simple prompts for interactive tutorials.

Does this TTS approach support local playback for accessibility workflows?

Yes, this TTS approach supports local playback integration specifically for accessibility workflows, allowing quick audio feedback in UIs and voice-enabled assistants without relying on external playback services.