skills.rest
srgaba
srgabaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

sag

Generates ElevenLabs text-to-speech audio with local playback via the sag CLI.

Updated Mar 30, 2026
Search Tags:#cli#text-to-speech#audio#elevenlabs#tts#voice generation#sag
One-click install
npx skills add https://github.com/srgaba/open-claw --skill sag-srgaba
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/srgaba/open-claw/tree/main/project/skills/sag
Command: npx skills add https://github.com/srgaba/open-claw --skill sag-srgaba

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Converting text into natural-sounding spoken audio requires managing ElevenLabs models, voices, pronunciation quirks, and playback, which is tedious to handle manually through raw API calls. ## Core Features & Use Cases - Text-to-Speech Generation: Speak any text locally with sag "Hello there", choosing voices with -v and saving output to files with -o. - Model & Voice Control: Select between expressive eleven_v3, stable eleven_multilingual_v2, or fast eleven_flash_v2_5, and list available voices with sag voices. - Expressive Delivery: Use v3 audio tags like [whispers], [laughs], and [short pause] plus normalization and language flags to control pronunciation and pacing. - Use Case: A user asks for a "crazy scientist voice" reply; generate the audio with sag -v Clawd -o /tmp/voice-reply.mp3 "..." and attach the file to the chat response. ## Quick Start Ask the assistant to say a short message out loud using the sag skill, for example by requesting a voice reply in a specific character 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 ElevenLabs from the command line?▼

Install the sag CLI via Homebrew and run `sag "Your text here"` to speak text aloud locally. Use `-v` to pick a voice and `-o` to save the audio to a file instead of playing it.

How do I add pauses and emotions to ElevenLabs v3 speech?▼

ElevenLabs v3 does not support SSML break tags; instead place audio tags like [short pause], [whispers], [laughs], or [excited] at the start of a line. For v2 models, SSML `<break time="1.5s" />` is supported.

What API key does the sag CLI require?▼

The sag CLI requires an ElevenLabs API key set as the ELEVENLABS_API_KEY environment variable, which is the preferred option. The SAG_API_KEY variable is also supported as an alternative.

Which ElevenLabs model should I use for text-to-speech?▼

Use eleven_v3 for expressive delivery with audio tags, eleven_multilingual_v2 for stable multilingual output, and eleven_flash_v2_5 when speed matters. The default is eleven_v3.

Why does ElevenLabs mispronounce names or numbers?▼

Mispronunciation happens when normalization or spelling confuses the model. Fix it by respelling words, adding hyphens, adjusting casing, using `--normalize auto` for numbers and URLs, or setting `--lang` to guide normalization.

Related Skills

Explore More Content & Communication Skills→
estebanrfpestebanrfp
1

sag

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

Community
Basic
NoizAINoizAI
525

sound-fx

Generate sound effects and ambient audio from text descriptions via the Noiz API.

Official
Basic
GetFresh-VenturesGetFresh-Ventures

voice-synth

Convert written briefs into TTS scripts with pronunciation guides and pacing markers.

Official
Intermediate
hasnahasna
24

Audio Generation

Generate MP3 audio from text using ElevenLabs, OpenAI TTS, or Google Text-to-Speech.

Official
Intermediate